WO2019206038A1 - 一种关注信息的处理方法及装置、存储介质、电子设备 - Google Patents

一种关注信息的处理方法及装置、存储介质、电子设备 Download PDF

Info

Publication number
WO2019206038A1
WO2019206038A1 PCT/CN2019/083442 CN2019083442W WO2019206038A1 WO 2019206038 A1 WO2019206038 A1 WO 2019206038A1 CN 2019083442 W CN2019083442 W CN 2019083442W WO 2019206038 A1 WO2019206038 A1 WO 2019206038A1
Authority
WO
WIPO (PCT)
Prior art keywords
display object
information
content data
attention
display
Prior art date
Application number
PCT/CN2019/083442
Other languages
English (en)
French (fr)
Inventor
彭彬绪
张帆
袁玮
简维
任小兵
于志兴
尹航飞
Original Assignee
北京市商汤科技开发有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 北京市商汤科技开发有限公司 filed Critical 北京市商汤科技开发有限公司
Priority to SG11202010556WA priority Critical patent/SG11202010556WA/en
Priority to JP2020558903A priority patent/JP7130771B2/ja
Publication of WO2019206038A1 publication Critical patent/WO2019206038A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01Input arrangements or combined input and output arrangements for interaction between user and computer

Definitions

  • the present application relates to the field of information statistics technologies, and in particular, to a method and device for processing information, a storage medium, and an electronic device.
  • a more common way to promote services is to recommend information to users through some multimedia platforms.
  • the information can be in image format or audio format.
  • Advertising, etc., is an example of advertising.
  • the recommendation of information lacks precision. If the information that the user does not like is displayed to the user blindly, not only will the multimedia resources be wasted, but also the user's stickyness to the multimedia resources will be reduced. The degree of attention of the recommended information has important reference value for subsequent accurate recommendations.
  • the embodiment of the present application provides a method and device for processing information of interest, a storage medium, and an electronic device.
  • the method further includes:
  • the acquiring the feature information of the at least one display object, and determining the attention information between the at least one display object and the first content data, based on the feature information of the at least one display object includes:
  • the attention information includes: indication information for indicating whether the display object pays attention to the first content data;
  • Determining the attention information between the at least one display object and the first content data based on the line of sight direction information of the at least one display object including:
  • the indication information corresponding to the display object is used to indicate that the display object pays attention to the first content data, for the display object whose line of sight falls into the first display area;
  • the indication information corresponding to the display object is used to indicate that the display object does not pay attention to the first content data.
  • the attention information further includes: displaying a degree of attention of the object to the first content data;
  • Determining the attention information between the at least one display object and the first content data based on the line of sight direction information of the at least one display object further comprising:
  • the attention information further includes: displaying a duration of attention of the object to the first content data;
  • Determining the attention information between the at least one display object and the first content data based on the line of sight direction information of the at least one display object further comprising:
  • the duration of the line of sight of the display object falling into the first display area is counted, and the display object is determined to be the first content data based on the calculated duration Pay attention to the length of time.
  • the obtaining the direction of the line of sight information of the at least one display object includes:
  • the acquiring the eyeball corner information and the head posture information of the at least one display object includes:
  • the image of the at least one display object is processed by the second neural network to obtain head pose information of the at least one display object.
  • the performing statistics on the first content data based on the attention information between the at least one display object and the first content data includes:
  • At least one of following attention information of the first content data is counted based on the attention information between the at least one display object and the first content data: a number of people who pay attention to the first content data, different concerns The number of people corresponding to the degree and the number of people corresponding to the length of attention.
  • the acquiring the feature information of the at least one display object, and determining the attention information between the at least one display object and the first content data, based on the feature information of the at least one display object includes:
  • the attention information includes: indication information for indicating whether the display object pays attention to the first content data;
  • Determining the attention information between the at least one display object and the first content data based on the geographic location information of the at least one display object including:
  • the indication information corresponding to the display object is used to indicate that the display object pays attention to the first content data
  • the indication information corresponding to the display object is used to indicate that the display object does not pay attention to the first content data.
  • the attention information further includes: displaying a duration of attention of the object to the first content data;
  • Determining the attention information between the at least one display object and the first content data based on the geographic location information of the at least one display object further comprising:
  • the performing statistics on the first content data based on the attention information between the at least one display object and the first content data includes:
  • At least one of following attention information of the first content data is counted based on the attention information between the at least one display object and the first content data: a number of people who pay attention to the first content data, different concerns The number of people corresponding to the duration.
  • the acquiring the feature information of the at least one display object, and determining the attention information between the at least one display object and the first content data, based on the feature information of the at least one display object includes:
  • the performing statistics on the first content data based on the attention information between the at least one display object and the first content data includes:
  • the following information about the first content data is counted: the number of people corresponding to different interaction frequencies.
  • a display unit configured to display the first content data
  • An obtaining unit configured to acquire feature information of at least one display object
  • a determining unit configured to determine, according to feature information of the at least one display object, attention information between the at least one display object and the first content data
  • a statistical unit configured to perform statistics of the attention information on the first content data based on the attention information between the at least one display object and the first content data.
  • the device further includes:
  • a recommendation unit configured to recommend second content data to be displayed based on the collected attention information
  • the display unit is further configured to display the second content data.
  • the acquiring unit is configured to acquire line-of-sight direction information of at least one display object
  • the determining unit is configured to determine the attention information between the at least one display object and the first content data based on the line of sight direction information of the at least one display object.
  • the attention information includes: indication information for indicating whether the display object pays attention to the first content data; the determining unit includes:
  • a first determining subunit configured to determine, according to the line of sight direction information of the at least one display object, whether a line of sight of the at least one display object falls within the first display area, where the first display area is the first content data a display area on the display device; the indication information corresponding to the display object is used to indicate that the display object pays attention to the first content data for a display object whose line of sight falls into the first display area; The display object corresponding to the first display area is not displayed, and the indication information corresponding to the display object is used to indicate that the display object does not pay attention to the first content data.
  • the attention information further includes: displaying a degree of attention of the object to the first content data; the determining unit further includes:
  • a second determining subunit configured to determine, for a display object in which the line of sight falls into the first display area, a line of sight of the display object to be projected to a target position of the first display area based on the line of sight direction information of the display object And determining, according to a positional relationship of the target location with respect to the first display area, a degree of attention of the display object to the first content data.
  • the attention information further includes: displaying a duration of attention of the object to the first content data; the determining unit further includes:
  • a third determining subunit configured to count, for a display object in which the line of sight falls into the first display area, a duration in which the line of sight of the display object falls into the first display area, and determine the display object based on the calculated duration The length of time of attention to the first content data.
  • the acquiring unit includes:
  • Obtaining a subunit configured to acquire eyeball corner information and head posture information of at least one display object
  • a calculating subunit configured to calculate line of sight direction information of the at least one display object based on the eyeball corner information and the head pose information of the at least one display object.
  • the acquiring subunit is configured as:
  • the image of the at least one display object is processed by the second neural network to obtain head pose information of the at least one display object.
  • the statistic unit is configured to perform statistics on at least one of the following information of the first content data based on the attention information between the at least one display object and the first content data. : the number of people who pay attention to the first content data, the number of people corresponding to different degrees of attention, and the number of people corresponding to different periods of attention.
  • the acquiring unit is configured to acquire geographic location information of at least one display object.
  • the determining unit is configured to determine the attention information between the at least one display object and the first content data based on the geographic location information of the at least one display object.
  • the attention information includes: indication information for indicating whether the display object pays attention to the first content data; the determining unit includes:
  • a fourth determining subunit configured to determine, according to geographic location information of the at least one display object, whether a location of the at least one display object falls within a first area range, the first area range being based on a location of the display device Determining; for the display object whose position falls within the range of the first area, the indication information corresponding to the display object is used to indicate that the display object pays attention to the first content data; a display object corresponding to the display object, where the indication information corresponding to the display object is used to indicate that the display object does not pay attention to the first content data.
  • the attention information further includes: displaying a duration of attention of the object to the first content data; the determining unit includes:
  • a fifth determining subunit configured to count, for a display object whose position falls within the first area range, a duration in which the position of the display object falls within the range of the first area, and determine the display object based on the calculated duration The length of time of attention to the first content data.
  • the statistic unit is configured to perform statistics on at least one of the following information of the first content data based on the attention information between the at least one display object and the first content data. : The number of people who pay attention to the first content data and the number of people corresponding to different durations of attention.
  • the acquiring unit is configured to acquire interaction information between the at least one display object and the first content data.
  • the determining unit is configured to determine the attention information between the at least one display object and the first content data based on the interaction information between the at least one display object and the first content data.
  • the statistic unit is configured to perform statistics on the following information of the first content data based on the attention information between the at least one display object and the first content data: different interaction frequencies The corresponding number of people.
  • the storage medium provided by the embodiment of the present application stores executable instructions, and the executable instructions are implemented by the processor to implement the processing method of the above-mentioned attention information.
  • a memory configured to store executable instructions
  • a processor configured to communicate with the memory to execute the executable instructions to implement the method of processing the above-described information of interest.
  • the first content data is displayed; the feature information of the at least one display object is obtained, and the at least one display object and the first content data are determined based on the feature information of the at least one display object.
  • Information of interest performing statistics on the information of interest on the first content data based on the attention information between the at least one display object and the first content data.
  • the technical solution of the embodiment of the present application implements statistics on the information of the first content data, and uses the statistical result as a basis or an influencing factor for the subsequent multimedia resource allocation, so as to implement information for the display object that meets the requirements of the display object itself. Accurate recommendation.
  • FIG. 1 is a network architecture diagram of an embodiment of the present application.
  • FIG. 2 is a schematic flowchart 1 of a method for processing information of interest according to an embodiment of the present application
  • FIG. 3 is a second schematic flowchart of a method for processing information of interest according to an embodiment of the present application.
  • FIG. 4 is a schematic flowchart 3 of a method for processing information of interest according to an embodiment of the present application.
  • FIG. 5 is a schematic flowchart 4 of a method for processing information of interest according to an embodiment of the present application
  • FIG. 6 is a schematic structural diagram 1 of a structure of a device for processing information of interest according to an embodiment of the present application
  • FIG. 7 is a second schematic structural diagram of a device for processing information of interest according to an embodiment of the present application.
  • FIG. 8 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
  • Embodiments of the present application can be applied to electronic devices such as computer systems/servers that can operate with numerous other general purpose or special purpose computing system environments or configurations.
  • Examples of well-known computing systems, environments, and/or configurations suitable for use with electronic devices such as computer systems/servers include, but are not limited to, personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop Devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, networked personal computers, small computer systems, mainframe computer systems, and distributed cloud computing technology environments including any of the above, and the like.
  • Electronic devices such as computer systems/servers can be described in the general context of computer system executable instructions (such as program modules) being executed by a computer system.
  • program modules may include routines, programs, target programs, components, logic, data structures, and the like that perform particular tasks or implement particular abstract data types.
  • the computer system/server can be implemented in a distributed cloud computing environment where tasks are performed by remote processing devices that are linked through a communication network.
  • program modules may be located on a local or remote computing system storage medium including storage devices.
  • FIG. 1 is a schematic diagram of hardware entities of various parties performing information interaction in the embodiment of the present application.
  • FIG. 1 includes: a server 11 . . . 1n, a display device 21-24, and a display device 21-24 performs a connection with a server through a wired network or a wireless network.
  • the display device is implemented by a mobile phone, a desktop computer, a PC, an all-in-one device, a VR device, an AR device, etc.
  • the server 11...1n can also communicate with the first type of terminal through the network (such as the terminal where the advertiser is located) , or the object that provides the creative and content promotion), the first type of terminal (such as the terminal where the advertiser is located, or the object that provides the creative and content promotion) will be submitted after the advertisement is submitted.
  • the first type of terminal such as the terminal where the advertiser is located, or the object that provides the creative and content promotion
  • Stored in a server cluster it can be equipped with a series of processes such as auditing the advertisements of the first type of terminals (such as the terminal where the advertiser is located, or the object that provides advertising and content promotion).
  • the terminal where the display device 21-24 is located may be referred to as a second type terminal (such as a general display), with respect to the terminal of the first type (such as the terminal where the advertiser is located, or the object that provides the promotion of the advertisement and the content promotion).
  • the terminal where the object is located, or the object that the ad is displayed or exposed all the applications installed in the display device or specified applications (such as game applications, video applications, navigation applications, etc.) can add advertisements to display more recommended information to the display objects.
  • FIG. 1 is only an example of a system architecture that implements the embodiments of the present application.
  • the embodiment of the present application is not limited to the system structure described in FIG. 1 above, and various embodiments of the present application are proposed based on the system architecture.
  • FIG. 2 is a schematic flowchart 1 of a method for processing information of interest according to an embodiment of the present application. As shown in FIG. 2, the method for processing the information of interest includes the following steps:
  • Step 201 Display the first content data.
  • the first content data may be any type of recommendation information, and the recommendation information may be, but not limited to, a still image, a moving image, a short video, a long video, an interactive game, and the like.
  • the first content data can be an advertisement.
  • the display device may be an ordinary display screen, an all-in-one machine, a projector, a virtual reality (VR) device, an augmented reality (AR) device, or the like.
  • a virtual reality (VR) device may be an augmented reality (AR) device, or the like.
  • AR augmented reality
  • Step 202 Acquire feature information of at least one display object, and determine, according to feature information of the at least one display object, attention information between the at least one display object and the first content data.
  • the display object may be a user, a robot, or another smart device.
  • the feature information includes at least one of the following: a line of sight direction information of the display object, geographic location information of the display object, and interaction information between the display object and the first content data.
  • the line of sight of the display object can represent whether the display object pays attention to the first content data. If the display object pays attention to the first content data, the display object can be further determined. The degree of attention to the first content data and the length of attention can be used to measure the exposure of the first content data to the display object.
  • the line-of-sight direction information of the display object can accurately indicate the attention information, and thus the attention information determined by displaying the line-of-sight direction information of the object is more in line with the true intention of the display object, and based on the attention information as a reference for the subsequent recommendation information, Achieve more accurate information recommendations.
  • the geographical location information of the display object may indicate whether the display object is located in the vicinity of the display device, and from another aspect, whether the first content data is paid attention to by the display object, if The display object pays attention to the first content data, and further determines the degree of attention and duration of attention of the display object to the first content data, and the attention information determined based on the geographic location information can also measure the first content data for display The exposure effect of the object.
  • the geographic location information of the display object can be obtained by the camera or the navigation and positioning system, so that the implementation is extremely convenient and fast, and the cost is low.
  • the information of interest determined by the geographical location information is used as a reference for subsequent recommendation information, and can be met.
  • the recommendation requirements of most of the display objects greatly improve the exposure of the recommended information.
  • the interaction of the display object with the first content data can also represent Whether the display object pays attention to the first content data, and if the display object pays attention to the first content data, further determining the frequency of interaction of the display object with the first content data (interaction operation triggered per unit time) The number of times), the attention information determined based on the interaction information can also measure the exposure effect of the first content data to the display object.
  • the interaction information of the display object can be directly obtained by the display device or the remote control device, and no additional equipment is needed for assistance, so the implementation is extremely convenient and fast, the cost is low, and the attention information determined by the interaction information can accurately indicate the attention.
  • Information based on this kind of attention information as a reference for subsequent recommendation information, can achieve more accurate information recommendation, more in line with the needs of the display object, so that the exposure effect of the recommendation information is greatly improved.
  • the different feature information may measure the attention information between the display object and the first content data from different dimensions.
  • the attention information between the at least one display object and the first content data may be determined based on a feature information.
  • the attention information between the at least one display object and the first content data may be determined based on two or three feature information.
  • Step 203 Perform statistics on the attention information on the first content data based on the attention information between the at least one display object and the first content data.
  • the at least one of the following information of the first content data is counted: the number of people who pay attention to the first content data, The number of people corresponding to different levels of attention, the number of people corresponding to different periods of interest, and the number of people corresponding to different frequency of interaction.
  • the method further includes: recommending second content data to be displayed based on the collected attention information; and displaying the second content data on the display device.
  • the content data displayed on the display device is randomly recommended by the server or the cloud, or may be personalized and recommended according to some reference information.
  • the server or the cloud does not obtain any reference information, the information is randomly recommended for the display object.
  • the server or the cloud obtains the reference information, and the information is personalizedly recommended for the display object according to the reference information.
  • the reference information may be a statistical result of performing attention information on each content data.
  • the reference information may be the number of people who pay attention to a certain information, or the number of people corresponding to different degrees of attention, or the number of people corresponding to different periods of attention, or the number of people corresponding to different frequency of interaction, and is not limited thereto, and may also be combined with these references. Any two or more of the information to implement the recommendation of the content data.
  • information 1 there are three candidate information, namely: information 1, information 2, and information 3.
  • information 1, information 2, and information 3 In a certain statistical period, the number of people who care about information 1 is 30, the number of people who care about information 2 is 20, and the number of people who care about information 3 is 3, then, information 1 is displayed as content data on the display device.
  • information 1, information 2, and information 3 there are three candidate information, namely: information 1, information 2, and information 3.
  • the number of people who care about information 1 is 30, the number of people who care about information 2 is 30, and the number of people who care about information 3 is 30, the number of people with a high level of attention on information 1 is 4, the number of people with a high level of attention on information 2 is 17, and the number of people with a high level of attention on information 3
  • information 2 is displayed as content data on the display device.
  • Information 2 is displayed as content data on the display device.
  • the number of interactions with the information 1 is 10
  • the number of interactions with the information 2 is 13 times.
  • the number of times of interaction with the information 3 is 0, and then the information 2 is displayed as content data on the display device.
  • FIG. 3 is a schematic flowchart 2 of a method for processing information of interest according to an embodiment of the present disclosure. As shown in FIG. 3, the method for processing the information of interest includes the following steps:
  • Step 301 Display the first content data.
  • the first content data may be any type of recommendation information, and the recommendation information may be, but not limited to, a still image, a moving image, a short video, a long video, an interactive game, and the like.
  • the first content data can be an advertisement.
  • the display device may be an ordinary display screen, an all-in-one machine, a projector, a VR device, an AR device, or the like.
  • the first content data displayed on the display device is randomly recommended by the server or the cloud, or may be personalized and recommended according to some reference information.
  • the server or the cloud does not obtain any reference information, the information is randomly recommended for the display object.
  • the server or the cloud obtains the reference information, and the information is personalizedly recommended for the display object according to the reference information.
  • the reference information may be a statistical result of performing attention information on each of the first content data.
  • Step 302 Acquire at least one line of sight direction information of the display object, and determine, according to the line of sight direction information of the at least one display object, the attention information between the at least one display object and the first content data.
  • the line of sight direction information of the at least one display object may be acquired based on the following manner:
  • the acquiring the eyeball corner information and the head posture information of the at least one display object includes:
  • the image of the at least one display object is processed by the second neural network to obtain head pose information of the at least one display object.
  • the target image (such as a face image) of five display objects (display object 1 to display object 5) within the shooting range supported by the camera can be acquired by the camera, which are P1, P2, P3, P4, P5, respectively.
  • the first neural network and the second neural network are respectively input, and P1 is taken as an example to obtain the eyeball angle prediction information eye1 of P1 by using the first neural network; and the head posture estimation of P1 is obtained by using the second neural network.
  • Information head1 Then, based on the eyeball angle prediction information eye1 and the head posture estimation information head1, the line of sight direction information of the display object 1 can be calculated. For the same reason of P2 to P5, the line-of-sight direction information of the display object 2 to the display object 5 can be obtained.
  • the attention information between the at least one display object and the first content data is determined based on the line of sight direction information of the at least one display object, where the attention information includes at least one of the following:
  • the attention information includes: indication information for indicating whether the display object pays attention to the first content data; and correspondingly, determining, according to the line of sight direction information of the at least one display object, Determining the attention information between the at least one display object and the first content data, comprising: determining, according to the line of sight direction information of the at least one display object, whether a line of sight of the at least one display object falls within the first display area,
  • the first display area is a display area of the first content data on the display device; and for a display object whose line of sight falls into the first display area, the indication information corresponding to the display object is used to indicate the display
  • the object is in focus on the first content data; the indication information corresponding to the display object is used to indicate that the display object does not perform the first content data, for the display object that does not fall into the first display area attention.
  • the line-of-sight direction information of five display objects is obtained, which are respectively S1, S2, S3, S4, and S5.
  • the line-of-sight direction information has different representations based on different coordinate systems.
  • S1 and S3 fall into the first display area where the first content data is located
  • S2, S4, and S5 do not fall into the first display area where the first content data is located
  • the display object 1 and the display object 3 are paired with the first content.
  • the data has been focused on, and the display object 2, the display object 4, and the display object 5 have not paid attention to the first content data.
  • the attention information includes: displaying a degree of attention of the object to the first content data; and determining, according to the line of sight direction information of the at least one display object, the at least one display object and the first
  • the attention information between the content data further includes: for the display object whose line of sight falls into the first display area, determining, according to the line of sight direction information of the display object, the line of sight of the display object to be projected to the first display a target location of the region, and determining a degree of attention of the display object to the first content data based on a location relationship of the target location relative to the first display region.
  • the line of sight direction information of the five display objects is obtained, which are S1, S2, S3, S4, and S5, respectively, where S1 and S3 fall into the first place where the first content data is located.
  • the display area, the display object 1 and the display object 3 pay attention to the first content data.
  • the degree of attention to the first content data may be projected to the target position T1 of the first display area according to S1. To measure, in an example, the closer the distance from the center O of the first display area is, the higher the degree of attention is.
  • the distance between the attention object F1 and the T1 to O of the display object 1 is In contrast, in the same way, the degree of attention F3 of the display object 3 to the first content data can be obtained.
  • the degree of attention may be quantized into several levels, for example, the distance from the center O is in the first adjacent range, the high attention level, and the distance from the center O is in the second adjacent range, the middle attention level, and The distance of the center O is in the third proximity range and is a low level of interest.
  • the attention information includes: a duration of attention of the display object to the first content data; and determining, according to the line of sight direction information of the at least one display object, the at least one display object and the first
  • the attention information between the content data further includes: counting, for the display object whose line of sight falls into the first display area, the duration of the line of sight of the display object falling into the first display area, based on the measured duration The duration of attention of the display object to the first content data.
  • the line of sight direction information of the five display objects is obtained, which are S1, S2, S3, S4, and S5, respectively, where S1 and S3 fall into the first place where the first content data is located.
  • the display object 1 and the display object 3 pay attention to the first content data.
  • the duration of the first content data is S1
  • the duration T1 of the first display area falls.
  • the duration of the attention to the first content data is the duration T3 of the S3 falling into the first display area.
  • the information of interest between the display object and the first content data may include one or more of the above information.
  • Step 303 Perform statistics on the attention information on the first content data based on the attention information between the at least one display object and the first content data.
  • step 302 different attention information can be used as different dimensions to provide an important reference for subsequent recommendation of information. Therefore, it is required to perform statistics on at least one of the following attention information of the first content data based on the attention information between the at least one display object and the first content data: a number of people who pay attention to the first content data, The number of people corresponding to different levels of attention, the number of people corresponding to different periods of interest, and the number of people corresponding to different frequency of interaction.
  • the information of the attention information is counted on the information 1, and at least one of the following information is obtained: the number of people who follow the information 1 is 20; the number of people who pay attention to the information 1 and the high level of interest There are 7 people, and the number of people who pay attention to information 1 and the level of interest is 6 , the number of people who pay attention to information 1 and the level of low attention is 7; the number of people who pay attention to information 1 and whose duration of attention is within the first time is 2, attention information 1 The number of people who are concerned that the duration is within the second duration is five, and the number of people who are concerned about information 1 and whose duration of attention is within the third duration is 13.
  • the above-mentioned different information can measure the attention of the display object to the first content data in different dimensions, and one or more of the above information can be used as a reference to measure the effective exposure degree of the first content data (ie, The degree of effective viewing) can provide an important reference for subsequent accurate recommendation of information.
  • the line-of-sight direction information of the display object can accurately indicate the attention information, and thus the attention information determined by displaying the line-of-sight direction information of the object is more in line with the true intention of the display object, and the follow-up information is used as the follow-up recommendation information.
  • the reference can achieve more accurate information recommendation and is more in line with the needs of the display objects.
  • FIG. 4 is a schematic flowchart 3 of a method for processing information of interest according to an embodiment of the present disclosure. As shown in FIG. 4, the method for processing the information of interest includes the following steps:
  • Step 401 Display the first content data.
  • the first content data may be any type of recommendation information, and the recommendation information may be, but not limited to, a still image, a moving image, a short video, a long video, an interactive game, and the like.
  • the first content data can be an advertisement.
  • the display device may be an ordinary display screen, an all-in-one machine, a projector, a VR device, an AR device, or the like.
  • Step 402 Acquire geographical location information of at least one display object, and determine, according to geographic location information of the at least one display object, the attention information between the at least one display object and the first content data.
  • the geographic location information of the at least one display object may be obtained based on the following manner:
  • the image of the at least one display object is processed by using a third neural network to obtain geographic location information of the at least one display object.
  • the geographic location information of the at least one display object can be obtained based on the following manner:
  • the GPS information of each display object terminal is acquired by a relay node (such as a wireless access node), thereby determining geographic location information of the at least one display object.
  • a relay node such as a wireless access node
  • the attention information between the at least one display object and the first content data is determined based on the geographical location information of the at least one display object, where the attention information includes at least one of the following:
  • the attention information includes: indication information for indicating whether the display object pays attention to the first content data; and correspondingly, determining, according to geographical location information of the at least one display object, Determining the attention information between the at least one display object and the first content data, including: determining, according to the geographical location information of the at least one display object, whether the location of the at least one display object falls within a range of the first region,
  • the first area range is determined based on the position of the display device (for example, the first area range is an area having a predetermined radius as a center radius of the display device); and the display object whose position falls within the first area range
  • the indication information corresponding to the display object is used to indicate that the display object pays attention to the first content data; and for the display object whose location does not fall within the first area range, the indication information corresponding to the display object is used. And indicating that the display object does not pay attention to the first content data.
  • the geographic location information of the five display objects is D1, D2, D3, D4, and D5. It should be understood that the geographic location information has different representations based on different coordinate systems. . Wherein, D1 and D3 fall within the first area, and D2, D4, and D5 do not fall within the first area of the first content data, and the display object 1 and the display object 3 pay attention to the first content data, and display The object 2, the display object 4, and the display object 5 do not pay attention to the first content data.
  • the attention information further includes: displaying a duration of attention of the object to the first content data; and determining, according to geographic location information of the at least one display object, the at least one display object and the The attention information between the first content data further includes: counting, for the display object whose position falls within the first area, the duration of the position of the display object falling within the range of the first area, based on the calculated duration Determining a duration of attention of the display object to the first content data.
  • the geographic location information of the five display objects is D1, D2, D3, D4, and D5, respectively, where D1 and D3 fall within the first area, and the display object 1 and the display object 3 pays attention to the first content data.
  • the duration of the first content data is the duration T1 of the range of the first region, and the display object 3 In other words, the duration of the first content data is the duration T3 in which the D3 falls within the range of the first region.
  • the information of interest between the display object and the first content data may include one or more of the above information.
  • Step 403 Acquire geographical location information of at least one display object, and determine, according to geographic location information of the at least one display object, the attention information between the at least one display object and the first content data.
  • step 402 different attention information can be used as different dimensions to provide an important reference for subsequent recommendation of information. Therefore, it is required to perform statistics on at least one of the following attention information of the first content data based on the attention information between the at least one display object and the first content data: a number of people who pay attention to the first content data, The number of people who have different time periods of interest.
  • the information of the attention information is collected for the information 1, and at least one of the following information is obtained: the number of people who care about the information 1 is 20; the information of interest 1 and the duration of the attention are located at the first The number of people in the duration is 2, the number of people who are concerned about information 1 and the duration of the second time is 5, and the number of people who are concerned about information 1 and whose duration of attention is within the third duration is 13.
  • the above-mentioned different information can measure the attention of the display object to the first content data in different dimensions, and one or more of the above information can be used as a reference to measure the effective exposure degree of the first content data (ie, The degree of effective viewing) can provide an important reference for subsequent accurate recommendation of information.
  • the geographic location information of the display object can be obtained by using a camera or a navigation and positioning system, so that the implementation is extremely convenient and fast, and the cost is low.
  • the attention information determined by the geographical location information is used as a reference for subsequent recommendation information. , can meet the recommendation requirements of most of the display objects, so that the exposure effect of the recommendation information is greatly improved.
  • FIG. 5 is a schematic flowchart diagram of a method for processing information of interest according to an embodiment of the present disclosure. As shown in FIG. 5, the method for processing the information of interest includes the following steps:
  • Step 501 Display the first content data.
  • the first content data may be any type of recommendation information, and the recommendation information may be, but not limited to, a still image, a moving image, a short video, a long video, an interactive game, and the like.
  • the first content data can be an advertisement.
  • the display device may be an ordinary display screen, an all-in-one machine, a projector, a VR device, an AR device, or the like.
  • Step 502 Acquire interaction information between the at least one display object and the first content data, and determine the at least one display object and the location based on interaction information between the at least one display object and the first content data. The information of interest between the first content data is described.
  • the interaction of the display object with the first content data can represent whether the display object has paid attention to the first content data, if the display object is A content data is followed, and the frequency of interaction of the display object with the first content data (the number of interactions triggered per unit time) can be further determined.
  • the attention information includes: interaction information between the display object and the first content data.
  • five display objects perform an interaction operation on the first content data, wherein in the statistical period, the number of times the display object 1 operates on the first content data is N1, and the display object 2 pairs The number of times the first content data is operated is N2, the number of times the display object 3 operates on the first content data is N3, and the number of times the display object 4 operates on the first content data is N4, and the display object 5 performs the first content data.
  • the number of operations is N5, then N1 to N5 can represent the interaction information between the five display objects and the first content data. Not limited to this, it is also possible to measure the interaction information according to the length of time each of the display objects operates on the first content data.
  • Step 503 Perform statistics on the attention information on the first content data based on the attention information between the at least one display object and the first content data.
  • step 502 different attention information can be used as different dimensions to provide an important reference for subsequent recommendation of information. Therefore, it is required to perform statistics on at least one of the following attention information of the first content data based on the attention information between the at least one display object and the first content data: a number of people corresponding to different interaction frequencies.
  • the information of the attention information is collected on the information 1, and the following information is obtained: the number of people interacting with the information 1 in the first frequency range is 6, and the information 1 The number of people who interacted in the second frequency range is 25.
  • the interaction information of the display object can be directly obtained by the display device or the remote control device, and no additional equipment is needed for assistance, so the implementation is extremely convenient and fast, and the cost is low, and the information of interest determined by the interaction information can be obtained.
  • Accurately indicating the information of interest, based on this kind of attention information as a reference for subsequent recommendation information, can achieve more accurate information recommendation, more in line with the needs of the display object, so that the exposure effect of the recommendation information is greatly improved.
  • FIG. 6 is a first schematic structural diagram of a structure of a device for processing information according to an embodiment of the present invention. As shown in FIG. 6, the device for processing the information of interest includes:
  • the display unit 601 is configured to display the first content data
  • the obtaining unit 602 is configured to acquire feature information of the at least one display object
  • the determining unit 603 is configured to determine, according to the feature information of the at least one display object, the attention information between the at least one display object and the first content data;
  • the statistics unit 604 is configured to perform statistics of the attention information on the first content data based on the attention information between the at least one display object and the first content data.
  • each unit in the processing device of the information of interest shown in FIG. 6 can be understood by referring to the related description of the processing method of the foregoing information.
  • the functions of the respective units in the processing device of the information of interest shown in FIG. 6 can be realized by a program running on the processor, or can be realized by a specific logic circuit.
  • FIG. 7 is a schematic structural diagram of a structure of a device for processing information of interest according to an embodiment of the present application. As shown in FIG. 7 , the device for processing the information of interest includes:
  • the display unit 601 is configured to display the first content data
  • the obtaining unit 602 is configured to acquire feature information of the at least one display object
  • the determining unit 603 is configured to determine, according to the feature information of the at least one display object, the attention information between the at least one display object and the first content data;
  • the statistics unit 604 is configured to perform statistics of the attention information on the first content data based on the attention information between the at least one display object and the first content data.
  • the device further includes:
  • the recommending unit 605 is configured to recommend the second content data to be displayed based on the collected attention information
  • the display unit is further configured to display the second content data on the display device.
  • the acquiring unit 602 is configured to acquire line-of-sight direction information of at least one display object
  • the determining unit 603 is configured to determine the attention information between the at least one display object and the first content data based on the line of sight direction information of the at least one display object.
  • the attention information includes: indication information for indicating whether the display object pays attention to the first content data; the determining unit 603 includes:
  • the first determining sub-unit 6031 is configured to determine, according to the line-of-sight direction information of the at least one display object, whether the line of sight of the at least one display object falls within the first display area, where the first display area is the first content a display area on the display device; the indication information corresponding to the display object is used to indicate that the display object pays attention to the first content data; For the display object whose line of sight does not fall into the first display area, the indication information corresponding to the display object is used to indicate that the display object does not pay attention to the first content data.
  • the attention information further includes: displaying a degree of attention of the object to the first content data; the determining unit 603 further includes:
  • a second determining sub-unit 6032 configured to determine, for a display object in which the line of sight falls within the first display area, a target of the display object to be projected to the first display area based on the line-of-sight direction information of the display object Positioning, and determining a degree of attention of the display object to the first content data based on a positional relationship of the target location with respect to the first display area.
  • the attention information further includes: displaying a duration of attention of the object to the first content data; the determining unit 603 further comprising:
  • the third determining sub-unit 6033 is configured to count, for the display object whose line of sight falls into the first display area, the duration of the line of sight of the display object falling into the first display area, and determine the display based on the measured duration The length of time that the object is interested in the first content data.
  • the obtaining unit 602 includes:
  • the obtaining subunit 6021 is configured to acquire eyeball corner information and head posture information of the at least one display object;
  • the calculating sub-unit 6022 is configured to calculate line-of-sight direction information of the at least one display object based on the eyeball corner information and the head posture information of the at least one display object.
  • the obtaining subunit 6021 is configured to:
  • the image of the at least one display object is processed by the second neural network to obtain head pose information of the at least one display object.
  • the statistics unit 604 is configured to perform at least one of the following information of the first content data based on the attention information between the at least one display object and the first content data.
  • Statistics The number of people who pay attention to the first content data, the number of people corresponding to different levels of attention, and the number of people corresponding to different periods of attention.
  • the acquiring unit 602 is configured to acquire geographic location information of at least one display object.
  • the determining unit 603 is configured to determine the attention information between the at least one display object and the first content data based on the geographical location information of the at least one display object.
  • the attention information includes: indication information for indicating whether the display object pays attention to the first content data; the determining unit 603 includes:
  • a fourth determining subunit 6034 configured to determine, according to geographic location information of the at least one display object, whether a location of the at least one display object falls within a first region range, the first region range being based on the display device Position determination; for the display object whose position falls within the range of the first area, the indication information corresponding to the display object is used to indicate that the display object pays attention to the first content data; An area-wide display object, the indication information corresponding to the display object is used to indicate that the display object does not pay attention to the first content data.
  • the attention information further includes: displaying a duration of attention of the object to the first content data; the determining unit 603 includes:
  • a fifth determining sub-unit 6035 configured to count, for a display object whose position falls within the first area range, a duration in which the position of the display object falls within the range of the first area, and determine the display based on the calculated duration The length of time that the object is interested in the first content data.
  • the statistics unit 604 is configured to perform at least one of the following information of the first content data based on the attention information between the at least one display object and the first content data.
  • Statistics The number of people who are concerned with the first content data and the number of people with different durations of interest.
  • the obtaining unit 602 is configured to acquire interaction information between the at least one display object and the first content data.
  • the determining unit 603 is configured to determine the attention information between the at least one display object and the first content data based on the interaction information between the at least one display object and the first content data.
  • the statistics unit 604 is configured to perform statistics on the following information of the first content data based on the attention information between the at least one display object and the first content data: different interactions The number of people corresponding to the frequency.
  • FIG. 8 is a schematic structural diagram of an application embodiment of an electronic device according to an embodiment of the present application.
  • the electronic device 1500 includes one or more processors and a communication unit.
  • the one or more processors may be stored in a read-only memory ( Various suitable actions and processes are performed by executable instructions in ROM) 1502 or executable instructions loaded into random access memory (RAM) 1503 from storage portion 1508.
  • the communication portion 1512 can include, but is not limited to, a network card, which can include, but is not limited to, an IB (Infiniband) network card, and the processor can communicate with the read only memory 1502 and/or the random access memory 1503 to execute executable instructions through the bus 1504. It is connected to the communication unit 1512 and communicates with other target devices via the communication unit 1512, thereby completing the operations corresponding to any of the methods provided by the embodiments of the present application.
  • RAM 1503 various programs and data required for the operation of the device can be stored.
  • the CPU 1501, the ROM 1502, and the RAM 1503 are connected to each other through a bus 1504.
  • ROM 1502 is an optional module.
  • the RAM 1503 stores executable instructions or writes executable instructions to the ROM 1502 at runtime, the executable instructions causing the processor 1501 to perform operations corresponding to the above-described communication methods.
  • An input/output (I/O) interface 1505 is also coupled to bus 1504.
  • the communication unit 1512 may be integrated or may be provided with a plurality of sub-modules (for example, a plurality of IB network cards) and on the bus link.
  • the following components are connected to the I/O interface 1505: an input portion 1506 including a keyboard, a mouse, etc.; an output portion 1507 including a cathode ray tube (CRT), a liquid crystal display (LCD), and the like, and a speaker; a storage portion 1508 including a hard disk or the like And a communication portion 1509 including a network interface card such as a LAN card, a modem, or the like.
  • the communication section 1509 performs communication processing via a network such as the Internet.
  • Driver 1510 is also coupled to I/O interface 1505 as needed.
  • a removable medium 1511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory or the like is mounted on the drive 1510 as needed so that a computer program read therefrom is installed into the storage portion 1508 as needed.
  • FIG. 8 is only an optional implementation manner.
  • the number and types of the components in FIG. 8 may be selected, deleted, added, or replaced according to actual needs; Different function components can also be implemented in separate settings or integrated settings, such as GPU and CPU detachable settings or GPU can be integrated on the CPU, the communication part can be separated, or integrated on the CPU or GPU. and many more. These alternative embodiments are all within the scope of protection disclosed herein.
  • an embodiment of the present disclosure includes a computer program product comprising a computer program tangibly embodied on a machine readable medium, the computer program comprising program code for executing the method illustrated in the flowchart, the program code comprising The instructions corresponding to the method steps provided by the embodiments of the present application are executed.
  • the computer program can be downloaded and installed from the network via the communication portion 1509, and/or installed from the removable medium 1511.
  • CPU central processing unit
  • the gaze tracking technical solution of the embodiment of the present application can be applied to various aspects such as driver monitoring, advertisement analysis, human-computer interaction, security monitoring, medical diagnosis, and psychology research.
  • the line of sight tracking method or device of the embodiment of the present application can determine the direction of the driver's line of sight, determine whether the point of interest is reasonable, and whether the driving behavior is consistent with the driving behavior, and can provide a reminder when the driver is distracted to assist in safety. travel.
  • the implementation direction can be obtained by the gaze tracking method or device of the embodiment of the present application, and the line of sight of the display object is estimated by the line of sight direction and the position of the human eye to perform human-computer interaction, such as a line of sight.
  • the direction of realization can be obtained by the gaze tracking method or device of the embodiment of the present application, and the direction of attention of the person is determined according to the direction of the line of sight of the person, and the subsequent behavior is predicted.
  • the methods, apparatus, and systems of the present application may be implemented in a number of ways.
  • the methods, apparatus, and systems of the present application can be implemented in software, hardware, firmware, or any combination of software, hardware, and firmware.
  • the above-described sequence of steps for the method is for illustrative purposes only, and the steps of the method of the present application are not limited to the order specifically described above unless otherwise specifically stated.
  • the present application can also be implemented as a program recorded in a recording medium, the programs including machine readable instructions for implementing the method according to the present application.
  • the present application also covers a recording medium storing a program for executing the method according to the present application.

Landscapes

  • Engineering & Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • User Interface Of Digital Computer (AREA)
  • Image Analysis (AREA)

Abstract

一种关注信息的处理方法及装置、存储介质、电子设备,所述方法包括:展示第一内容数据(201);获取至少一个展示对象的特征信息,基于所述至少一个展示对象的特征信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息(202);基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据进行关注信息的统计(203)。

Description

一种关注信息的处理方法及装置、存储介质、电子设备
相关申请的交叉引用
本申请基于申请号为201810374723.6、申请日为2018年04月24日的中国专利申请提出,并要求该中国专利申请的优先权,该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本申请涉及信息统计技术领域,尤其涉及一种关注信息的处理方法及装置、存储介质、电子设备。
背景技术
随着科技的发展,各大商家利用各种各样的方式进行自身服务的推广,一种较为常见的服务推广方式是通过一些多媒体平台为用户推荐信息,这些信息可以是图像形式、音频形式、视频形式等等,广告就是一种例子。
随着推荐信息的爆发式增长,信息的推荐缺乏精准度,如果将用户不喜欢的信息一味的展示给用户,不但会浪费多媒体资源还会导致用户对多媒体资源的粘性降低,可见,用户对某个推荐信息的关注程度对后续的精准推荐具有重要参考价值。
发明内容
为解决上述技术问题,本申请实施例提供了一种关注信息的处理方法及装置、存储介质、电子设备。
本申请实施例提供的关注信息的处理方法,包括:
展示第一内容数据;
获取至少一个展示对象的特征信息,基于所述至少一个展示对象的特征信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息;
基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据进行关注信息的统计。
本申请实施例中,所述方法还包括:
基于所统计出的关注信息,推荐待展示的第二内容数据;
展示所述第二内容数据。
本申请实施例中,所述获取至少一个展示对象的特征信息,基于所述至少一个展示对象的特征信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息,包括:
获取至少一个展示对象的视线方向信息,基于所述至少一个展示对象的视线方向信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息。
本申请实施例中,所述关注信息包括:用于指示展示对象是否对所述第一内容数据进行关注的指示信息;
所述基于所述至少一个展示对象的视线方向信息,确定所述至少一个展示对象与所 述第一内容数据之间的关注信息,包括:
基于所述至少一个展示对象的视线方向信息,确定所述至少一个展示对象的视线是否落入第一显示区域,所述第一显示区域为所述第一内容数据在所述显示装置上的显示区域;
对于视线落入所述第一显示区域的展示对象,所述展示对象对应的指示信息用于指示所述展示对象对所述第一内容数据进行关注;
对于视线未落入所述第一显示区域的展示对象,所述展示对象对应的指示信息用于指示所述展示对象对所述第一内容数据未进行关注。
本申请实施例中,所述关注信息还包括:展示对象对所述第一内容数据的关注程度;
所述基于所述至少一个展示对象的视线方向信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息,还包括:
对于视线落入所述第一显示区域的展示对象,基于所述展示对象的视线方向信息,确定所述展示对象的视线投射到所述第一显示区域的目标位置,并基于所述目标位置相对于所述第一显示区域的位置关系,确定所述展示对象对所述第一内容数据的关注程度。
本申请实施例中,所述关注信息还包括:展示对象对所述第一内容数据的关注时长;
所述基于所述至少一个展示对象的视线方向信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息,还包括:
对于视线落入所述第一显示区域的展示对象,统计所述展示对象的视线落入所述第一显示区域的时长,基于所统计的时长确定所述展示对象对所述第一内容数据的关注时长。
本申请实施例中,所述获取至少一个展示对象的视线方向信息,包括:
获取至少一个展示对象的眼珠转角信息和头部姿态信息;
基于所述至少一个展示对象的眼珠转角信息和头部姿态信息,计算所述至少一个展示对象的视线方向信息。
本申请实施例中,所述获取至少一个展示对象的眼珠转角信息和头部姿态信息,包括:
获取所述至少一个展示对象的图像;
利用第一神经网络对所述至少一个展示对象的图像进行处理,得到所述至少一个展示对象的眼珠转角信息;
利用第二神经网络对所述至少一个展示对象的图像进行处理,得到所述至少一个展示对象的头部姿态信息。
本申请实施例中,所述基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据进行关注信息的统计,包括:
基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据的如下关注信息的至少之一进行统计:关注所述第一内容数据的人数、不同关注程度对应的人数、不同关注时长对应的人数。
本申请实施例中,所述获取至少一个展示对象的特征信息,基于所述至少一个展示对象的特征信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息,包括:
获取至少一个展示对象的地理位置信息,基于所述至少一个展示对象的地理位置信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息。
本申请实施例中,所述关注信息包括:用于指示展示对象是否对所述第一内容数据进行关注的指示信息;
所述基于所述至少一个展示对象的地理位置信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息,包括:
基于所述至少一个展示对象的地理位置信息,确定所述至少一个展示对象的位置是否落入第一区域范围,所述第一区域范围基于所述显示装置的位置确定;
对于位置落入所述第一区域范围的展示对象,所述展示对象对应的指示信息用于指示所述展示对象对所述第一内容数据进行关注;
对于位置未落入所述第一区域范围的展示对象,所述展示对象对应的指示信息用于指示所述展示对象对所述第一内容数据未进行关注。
本申请实施例中,所述关注信息还包括:展示对象对所述第一内容数据的关注时长;
所述基于所述至少一个展示对象的地理位置信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息,还包括:
对于位置落入所述第一区域范围的展示对象,统计所述展示对象的位置落入所述第一区域范围的时长,基于所统计的时长确定所述展示对象对所述第一内容数据的关注时长。
本申请实施例中,所述基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据进行关注信息的统计,包括:
基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据的如下关注信息的至少之一进行统计:关注所述第一内容数据的人数、不同关注时长对应的人数。
本申请实施例中,所述获取至少一个展示对象的特征信息,基于所述至少一个展示对象的特征信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息,包括:
获取至少一个展示对象与所述第一内容数据之间的交互信息,基于所述至少一个展示对象与所述第一内容数据之间的交互信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息。
本申请实施例中,所述基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据进行关注信息的统计,包括:
基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据的如下关注信息进行统计:不同交互频次对应的人数。
本申请实施例提供的关注信息的处理装置,包括:
显示单元,配置为展示第一内容数据;
获取单元,配置为获取至少一个展示对象的特征信息;
确定单元,配置为基于所述至少一个展示对象的特征信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息;
统计单元,配置为基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据进行关注信息的统计。
本申请实施例中,所述装置还包括:
推荐单元,配置为基于所统计出的关注信息,推荐待展示的第二内容数据;
所述展示单元,还配置为展示所述第二内容数据。
本申请实施例中,所述获取单元,配置为获取至少一个展示对象的视线方向信息;
所述确定单元,配置为基于所述至少一个展示对象的视线方向信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息。
本申请实施例中,所述关注信息包括:用于指示展示对象是否对所述第一内容数据进行关注的指示信息;所述确定单元包括:
第一确定子单元,配置为基于所述至少一个展示对象的视线方向信息,确定所述至少一个展示对象的视线是否落入第一显示区域,所述第一显示区域为所述第一内容数据在所述显示装置上的显示区域;对于视线落入所述第一显示区域的展示对象,所述展示对象对应的指示信息用于指示所述展示对象对所述第一内容数据进行关注;对于视线未落入所述第一显示区域的展示对象,所述展示对象对应的指示信息用于指示所述展示对象对所述第一内容数据未进行关注。
本申请实施例中,所述关注信息还包括:展示对象对所述第一内容数据的关注程度;所述确定单元还包括:
第二确定子单元,配置为对于视线落入所述第一显示区域的展示对象,基于所述展示对象的视线方向信息,确定所述展示对象的视线投射到所述第一显示区域的目标位置,并基于所述目标位置相对于所述第一显示区域的位置关系,确定所述展示对象对所述第一内容数据的关注程度。
本申请实施例中,所述关注信息还包括:展示对象对所述第一内容数据的关注时长;所述确定单元还包括:
第三确定子单元,配置为对于视线落入所述第一显示区域的展示对象,统计所述展示对象的视线落入所述第一显示区域的时长,基于所统计的时长确定所述展示对象对所述第一内容数据的关注时长。
本申请实施例中,所述获取单元包括:
获取子单元,配置为获取至少一个展示对象的眼珠转角信息和头部姿态信息;
计算子单元,配置为基于所述至少一个展示对象的眼珠转角信息和头部姿态信息,计算所述至少一个展示对象的视线方向信息。
本申请实施例中,所述获取子单元,配置为:
获取所述至少一个展示对象的图像;
利用第一神经网络对所述至少一个展示对象的图像进行处理,得到所述至少一个展示对象的眼珠转角信息;
利用第二神经网络对所述至少一个展示对象的图像进行处理,得到所述至少一个展示对象的头部姿态信息。
本申请实施例中,所述统计单元,配置为基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据的如下关注信息的至少之一进行统计:关注所述第一内容数据的人数、不同关注程度对应的人数、不同关注时长对应的人数。
本申请实施例中,所述获取单元,配置为获取至少一个展示对象的地理位置信息;
所述确定单元,配置为基于所述至少一个展示对象的地理位置信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息。
本申请实施例中,所述关注信息包括:用于指示展示对象是否对所述第一内容数据进行关注的指示信息;所述确定单元包括:
第四确定子单元,配置为基于所述至少一个展示对象的地理位置信息,确定所述至少一个展示对象的位置是否落入第一区域范围,所述第一区域范围基于所述显示装置的位置确定;对于位置落入所述第一区域范围的展示对象,所述展示对象对应的指示信息用于指示所述展示对象对所述第一内容数据进行关注;对于位置未落入所述第一区域范围的展示对象,所述展示对象对应的指示信息用于指示所述展示对象对所述第一内容数据未进行关注。
本申请实施例中,所述关注信息还包括:展示对象对所述第一内容数据的关注时长;所述确定单元包括:
第五确定子单元,配置为对于位置落入所述第一区域范围的展示对象,统计所述展 示对象的位置落入所述第一区域范围的时长,基于所统计的时长确定所述展示对象对所述第一内容数据的关注时长。
本申请实施例中,所述统计单元,配置为基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据的如下关注信息的至少之一进行统计:关注所述第一内容数据的人数、不同关注时长对应的人数。
本申请实施例中,所述获取单元,配置为获取至少一个展示对象与所述第一内容数据之间的交互信息;
所述确定单元,配置为基于所述至少一个展示对象与所述第一内容数据之间的交互信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息。
本申请实施例中,所述统计单元,配置为基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据的如下关注信息进行统计:不同交互频次对应的人数。
本申请实施例提供的存储介质上存储有可执行指令,该可执行指令被处理器执行时实现上述的关注信息的处理方法。
本申请实施例提供的电子设备,包括:
存储器,配置为存储可执行指令;
处理器,配置为与所述存储器通信以执行所述可执行指令从而实现上述的关注信息的处理方法。
本申请实施例的技术方案中,展示第一内容数据;获取至少一个展示对象的特征信息,基于所述至少一个展示对象的特征信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息;基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据进行关注信息的统计。采用本申请实施例的技术方案,实现了对第一内容数据的关注信息的统计,将统计结果作为后续多媒体资源分配的依据或影响因素,从而实现为展示对象推荐符合展示对象自身需求的信息的精准推荐。
附图说明
图1为本申请实施例的网络架构图;
图2为本申请实施例的关注信息的处理方法的流程示意图一;
图3为本申请实施例的关注信息的处理方法的流程示意图二;
图4为本申请实施例的关注信息的处理方法的流程示意图三;
图5为本申请实施例的关注信息的处理方法的流程示意图四;
图6为本申请实施例的关注信息的处理装置的结构组成示意图一;
图7为本申请实施例的关注信息的处理装置的结构组成示意图二;
图8为本申请实施例的电子设备的结构组成示意图。
具体实施方式
现在将参照附图来详细描述本申请的各种示例性实施例。应注意到:除非另外具体说明,否则在这些实施例中阐述的部件和步骤的相对布置、数字表达式和数值不限制本申请的范围。
同时,应当明白,为了便于描述,附图中所示出的各个部分的尺寸并不是按照实际的比例关系绘制的。
以下对至少一个示例性实施例的描述实际上仅仅是说明性的,决不作为对本申请及其应用或使用的任何限制。
对于相关领域普通技术人员已知的技术、方法和设备可能不作详细讨论,但在适当情况下,所述技术、方法和设备应当被视为说明书的一部分。
应注意到:相似的标号和字母在下面的附图中表示类似项,因此,一旦某一项在一个附图中被定义,则在随后的附图中不需要对其进行进一步讨论。
本申请实施例可以应用于计算机系统/服务器等电子设备,其可与众多其它通用或专用计算系统环境或配置一起操作。适于与计算机系统/服务器等电子设备一起使用的众所周知的计算系统、环境和/或配置的例子包括但不限于:个人计算机系统、服务器计算机系统、瘦客户机、厚客户机、手持或膝上设备、基于微处理器的系统、机顶盒、可编程消费电子产品、网络个人电脑、小型计算机系统、大型计算机系统和包括上述任何系统的分布式云计算技术环境,等等。
计算机系统/服务器等电子设备可以在由计算机系统执行的计算机系统可执行指令(诸如程序模块)的一般语境下描述。通常,程序模块可以包括例程、程序、目标程序、组件、逻辑、数据结构等等,它们执行特定的任务或者实现特定的抽象数据类型。计算机系统/服务器可以在分布式云计算环境中实施,分布式云计算环境中,任务是由通过通信网络链接的远程处理设备执行的。在分布式云计算环境中,程序模块可以位于包括存储设备的本地或远程计算系统存储介质上。
图1为本申请实施例中进行信息交互的各方硬件实体的示意图,图1中包括:服务器11……1n、显示装置21-24,显示装置21-24通过有线网络或者无线网络与服务器进行信息交互,显示装置通过手机、台式机、PC机、一体机、VR设备、AR设备等实现,一个示例中,服务器11……1n还可以通过网络与第一类终端(如广告主所在的终端,或称为提供广告素材和内容推广的对象)进行交互,第一类终端(如广告主所在的终端,或称为提供广告素材和内容推广的对象)将想要投放的广告提交后,被存储在服务器集群中,可以配备管理员对第一类终端(如广告主所在的终端,或称为提供广告素材和内容推广的对象)投放的广告进行审核等一系列处理。其中,相对于第一类终端(如广告主所在的终端,或称为提供广告素材和内容推广的对象)而言,显示装置21-24所在的终端可以称为第二类终端(如普通展示对象所在的终端,或称为广告展示或曝光的对象)。其中,显示装置中安装的所有应用或者指定的应用(如游戏应用,视频应用,导航应用等等)都可以添加广告以展示给展示对象更多的推荐信息。
上述图1的例子只是实现本申请实施例的一个系统架构实例,本申请实施例并不限于上述图1所述的系统结构,基于该系统架构,提出本申请各个实施例。
图2为本申请实施例的关注信息的处理方法的流程示意图一,如图2所示,所述关注信息的处理方法包括以下步骤:
步骤201:展示第一内容数据。
本申请实施例中,第一内容数据可以是任意一种推荐信息,推荐信息可以但不局限于是静态图像、动态图像、短视频、长视频、互动游戏等等。在一个例子中,第一内容数据可以是广告。
本申请实施例中,显示装置可以是普通的显示屏、一体机、投影仪、虚拟现实(VR,Virtual Reality)设备、增强现实(AR,Augmented Reality)设备等等。
步骤202:获取至少一个展示对象的特征信息,基于所述至少一个展示对象的特征信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息。
这里,展示对象可以是用户、也可以是机器人、还可以是其他智能设备。
本申请实施例中,所述特征信息包括以下至少一种:展示对象的视线方向信息、展示对象的地理位置信息、展示对象与所述第一内容数据之间的交互信息。
以展示对象的视线方向信息为例,展示对象的视线可以代表该展示对象对第一内容 数据是否进行了关注,如果该展示对象对第一内容数据进行了关注,进一步还可以确定出该展示对象对第一内容数据的关注程度和关注时长,这些关注信息都可以来衡量第一内容数据面向展示对象的曝光效果。
这里,展示对象的视线方向信息能够准确地表明关注信息,因而通过展示对象的视线方向信息所确定的关注信息也更加符合展示对象的真实意图,基于这种关注信息作为后续推荐信息的参考,能够实现更加精准的信息推荐。
以展示对象的地理位置信息为例,展示对象的地理位置信息可以表明该展示对象是否位于显示装置的附近,从另一个方面也能代表该展示对象对第一内容数据是否进行了关注,如果该展示对象对第一内容数据进行了关注,进一步还可以确定出该展示对象对第一内容数据的关注程度和关注时长,这些基于地理位置信息确定的关注信息也可以来衡量第一内容数据面向展示对象的曝光效果。
这里,展示对象的地理位置信息可以通过摄像头、或导航定位系统来获取得到,因而实现起来极为方便快捷,成本较低,通过地理位置信息所确定的关注信息作为后续推荐信息的参考,可以实现符合大部分展示对象的推荐需求,使得推荐信息的曝光效果大大提高。
以展示对象与所述第一内容数据之间的交互信息为例,展示对象对第一内容数据的交互(如浏览操作、下载操作、点赞操作、关注操作、点击操作等等)也能代表该展示对象对第一内容数据是否进行了关注,如果该展示对象对第一内容数据进行了关注,进一步还可以确定出该展示对象对第一内容数据的交互频次(单位时间内触发的交互操作的次数),这些基于交互信息确定的关注信息也可以来衡量第一内容数据面向展示对象的曝光效果。
这里,展示对象的交互信息可以直接通过显示装置或远程遥控装置获取得到,无需额外的设备来辅助,因而实现起来极为方便快捷,成本较低,通过交互信息所确定的关注信息能够准确地表明关注信息,基于这种关注信息作为后续推荐信息的参考,能够实现更加精准的信息推荐,更加符合展示对象的需求,使得推荐信息的曝光效果大大提高。
这里,不同的特征信息可以从不同的维度来衡量展示对象与所述第一内容数据之间的关注信息。在一个例子中,可以基于一种特征信息确定所述至少一个展示对象与所述第一内容数据之间的关注信息。在另一个例子中,可以基于两种或三种特征信息确定所述至少一个展示对象与所述第一内容数据之间的关注信息。
步骤203:基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据进行关注信息的统计。
例如:基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据的如下关注信息的至少之一进行统计:关注所述第一内容数据的人数、不同关注程度对应的人数、不同关注时长对应的人数、不同交互频次对应的人数。
可选地,所述方法还包括:基于所统计出的关注信息,推荐待展示的第二内容数据;在所述显示装置上展示所述第二内容数据。
在一实施方式中,在显示装置上所展示的内容数据是服务器或者云端随机推荐的,也可以是根据某个参考信息进行个性化推荐的。在一个例子中,服务器或者云端未获取到任何参考信息的情况下,为展示对象随机推荐信息。在另一个例子中,服务器或者云端获取到了参考信息,则根据该参考信息为展示对象个性化地推荐信息。这里,参考信息可以是对各个内容数据进行关注信息的统计得到。
这里,参考信息可以是关注某个信息的人数、或者是不同关注程度对应的人数、或者是不同关注时长对应的人数、或者是不同交互频次对应的人数,不局限于此,也可以结合这些参考信息中的任意两个或更多个来实现内容数据的推荐。
例如有三个候选信息,分别为:信息1、信息2、信息3,其中在某个统计周期内,关注信息1的人数为30个,关注信息2的人数为20个,关注信息3的人数为3个,那么,就将信息1作为内容数据展示在显示装置上。
例如有三个候选信息,分别为:信息1、信息2、信息3,其中在某个统计周期内,关注信息1的人数为30个,关注信息2的人数为30个,关注信息3的人数为30个,在信息1上关注程度处于高等级关注度的人数为4个,在信息2上关注程度处于高等级关注度的人数为17个,在信息3上关注程度处于高等级关注度的人数为12个,那么,就将信息2作为内容数据展示在显示装置上。
例如有三个候选信息,分别为:信息1、信息2、信息3,其中在某个统计周期内,关注信息1的人数为30个,关注信息2的人数为30个,关注信息3的人数为30个,在信息1上关注时长超过3分钟的人数为4个,在信息2上关注时长超过3分钟的人数为17个,在信息3上关注时长超过3分钟的人数为12个,那么,就将信息2作为内容数据展示在显示装置上。
例如有三个候选信息,分别为:信息1、信息2、信息3,其中在某个统计周期内,与信息1进行交互操作的次数为10次,与信息2进行交互操作的次数为13次,与信息3进行交互操作的次数为0次,那么,就将信息2作为内容数据展示在显示装置上。
图3为本申请实施例的关注信息的处理方法的流程示意图二,如图3所示,所述关注信息的处理方法包括以下步骤:
步骤301:展示第一内容数据。
本申请实施例中,第一内容数据可以是任意一种推荐信息,推荐信息可以但不局限于是静态图像、动态图像、短视频、长视频、互动游戏等等。在一个例子中,第一内容数据可以是广告。
本申请实施例中,显示装置可以是普通的显示屏、一体机、投影仪、VR设备、AR设备等等。
在一实施方式中,在显示装置上所展示的第一内容数据是服务器或者云端随机推荐的,也可以是根据某个参考信息进行个性化推荐的。在一个例子中,服务器或者云端未获取到任何参考信息的情况下,为展示对象随机推荐信息。在另一个例子中,服务器或者云端获取到了参考信息,则根据该参考信息为展示对象个性化地推荐信息。这里,参考信息可以是对各个第一内容数据进行关注信息的统计得到。
步骤302:获取至少一个展示对象的视线方向信息,基于所述至少一个展示对象的视线方向信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息。
在一实施方式中,可以基于以下方式获取至少一个展示对象的视线方向信息:
获取至少一个展示对象的眼珠转角信息和头部姿态信息;
基于所述至少一个展示对象的眼珠转角信息和头部姿态信息,计算所述至少一个展示对象的视线方向信息。
进一步,所述获取至少一个展示对象的眼珠转角信息和头部姿态信息,包括:
获取所述至少一个展示对象的图像;
利用第一神经网络对所述至少一个展示对象的图像进行处理,得到所述至少一个展示对象的眼珠转角信息;
利用第二神经网络对所述至少一个展示对象的图像进行处理,得到所述至少一个展示对象的头部姿态信息。
例如:通过摄像头可以采集到该摄像头支持的拍摄范围内的5个展示对象(展示对象1至展示对象5)的目标图像(如人脸图像),分别为P1、P2、P3、P4、P5,对于各个目标图像,分别输入第一神经网络和第二神经网络,以P1为例,利用第一神经网络 获取P1的眼珠转角预估信息eye1;利用第二神经网络获取P1的头部姿态预估信息head1。然后,基于眼珠转角预估信息eye1和头部姿态预估信息head1可以计算得到展示对象1的视线方向信息。对于P2至P5同理,可以得到展示对象2至展示对象5的视线方向信息。
本申请实施例中,基于所述至少一个展示对象的视线方向信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息,这里,所述关注信息包括以下至少之一:
1)用于指示展示对象是否对所述第一内容数据进行关注的指示信息;
2)展示对象对所述第一内容数据的关注程度;
3)展示对象对所述第一内容数据的关注时长。
在一实施方式中,所述关注信息包括:用于指示展示对象是否对所述第一内容数据进行关注的指示信息;相应地,所述基于所述至少一个展示对象的视线方向信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息,包括:基于所述至少一个展示对象的视线方向信息,确定所述至少一个展示对象的视线是否落入第一显示区域,所述第一显示区域为所述第一内容数据在所述显示装置上的显示区域;对于视线落入所述第一显示区域的展示对象,所述展示对象对应的指示信息用于指示所述展示对象对所述第一内容数据进行关注;对于视线未落入所述第一显示区域的展示对象,所述展示对象对应的指示信息用于指示所述展示对象对所述第一内容数据未进行关注。
例如:获取到5个展示对象(展示对象1至展示对象5)的视线方向信息,分别为S1、S2、S3、S4、S5,应理解,视线方向信息基于不同的坐标系具有不同的表示形式。其中,S1、S3落入了第一内容数据所在的第一显示区域,S2、S4、S5未落入第一内容数据所在的第一显示区域,则展示对象1和展示对象3对第一内容数据进行了关注,展示对象2、展示对象4以及展示对象5未对第一内容数据进行关注。
在一实施方式中,所述关注信息包括:展示对象对所述第一内容数据的关注程度;所述基于所述至少一个展示对象的视线方向信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息,还包括:对于视线落入所述第一显示区域的展示对象,基于所述展示对象的视线方向信息,确定所述展示对象的视线投射到所述第一显示区域的目标位置,并基于所述目标位置相对于所述第一显示区域的位置关系,确定所述展示对象对所述第一内容数据的关注程度。
例如:获取到5个展示对象(展示对象1至展示对象5)的视线方向信息,分别为S1、S2、S3、S4、S5,其中,S1、S3落入了第一内容数据所在的第一显示区域,则展示对象1和展示对象3对第一内容数据进行了关注,对于展示对象1而言,其关注第一内容数据的程度可以根据S1投射到所述第一显示区域的目标位置T1来衡量,在一个例子中,距离第一显示区域中心O的距离越近,则关注程度越高,基于此,展示对象1对第一内容数据的关注程度F1与T1到O之间的距离成反比,同理,可以得出展示对象3对第一内容数据的关注程度F3。在一实施方式中,可以将关注程度量化为几个等级,例如与中心O的距离处于第一临近范围的为高关注等级、与中心O的距离处于第二临近范围的为中关注等级、与中心O的距离处于第三临近范围的为低关注等级。
在一实施方式中,所述关注信息包括:展示对象对所述第一内容数据的关注时长;所述基于所述至少一个展示对象的视线方向信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息,还包括:对于视线落入所述第一显示区域的展示对象,统计所述展示对象的视线落入所述第一显示区域的时长,基于所统计的时长确定所述展示对象对所述第一内容数据的关注时长。
例如:获取到5个展示对象(展示对象1至展示对象5)的视线方向信息,分别为S1、S2、S3、S4、S5,其中,S1、S3落入了第一内容数据所在的第一显示区域,则展 示对象1和展示对象3对第一内容数据进行了关注,对于展示对象1而言,其关注第一内容数据的时长为S1落入所述第一显示区域的时长T1,同理,对于展示对象3而言,其关注第一内容数据的时长为S3落入所述第一显示区域的时长T3。
本申请实施例中,展示对象与第一内容数据之间的关注信息可以包括上述其中一种或任意两种以上信息。
步骤303:基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据进行关注信息的统计。
承接步骤302,不同的关注信息可以作为不同的维度来对后续进行信息的推荐提供重要的参考。因此需要基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据的如下关注信息的至少之一进行统计:关注所述第一内容数据的人数、不同关注程度对应的人数、不同关注时长对应的人数、不同交互频次对应的人数。
在一个例子中,在统计周期(如3个小时)内,对信息1进行关注信息的统计,得到如下至少一种信息:关注信息1的人数为20个;关注信息1且高关注等级的人数为7个,关注信息1且中关注等级的人数为6个,关注信息1且低关注等级的人数为7个;关注信息1且关注时长位于第一时长范围内的人数为2个,关注信息1且关注时长位于第二时长范围内的人数为5个,关注信息1且关注时长位于第三时长范围内的人数为13个。
上述统计出的不同信息在不同的维度均可以衡量展示对象对第一内容数据的关注情况,可以将上述信息的一种或多种作为参考,来衡量第一内容数据的有效曝光程度(也即有效被观看的程度),从而可以为后续进行信息的精准推荐提供重要的参考。
本申请实施例中,展示对象的视线方向信息能够准确地表明关注信息,因而通过展示对象的视线方向信息所确定的关注信息也更加符合展示对象的真实意图,基于这种关注信息作为后续推荐信息的参考,能够实现更加精准的信息推荐,更加符合展示对象的需求。
图4为本申请实施例的关注信息的处理方法的流程示意图三,如图4所示,所述关注信息的处理方法包括以下步骤:
步骤401:展示第一内容数据。
本申请实施例中,第一内容数据可以是任意一种推荐信息,推荐信息可以但不局限于是静态图像、动态图像、短视频、长视频、互动游戏等等。在一个例子中,第一内容数据可以是广告。
本申请实施例中,显示装置可以是普通的显示屏、一体机、投影仪、VR设备、AR设备等等。
步骤402:获取至少一个展示对象的地理位置信息,基于所述至少一个展示对象的地理位置信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息。
在一实施方式中,可以基于以下方式获取至少一个展示对象的地理位置信息:
获取所述至少一个展示对象的图像;
利用第三神经网络对所述至少一个展示对象的图像进行处理,得到所述至少一个展示对象的地理位置信息。
在另一实施方式中,可以基于以下方式获取至少一个展示对象的地理位置信息:
通过中继节点(如无线接入节点)获取各个展示对象终端的GPS信息,从而确定所述至少一个展示对象的地理位置信息。
本申请实施例中,基于所述至少一个展示对象的地理位置信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息,这里,所述关注信息包括以下至少之一:
1)用于指示展示对象是否对所述第一内容数据进行关注的指示信息;
2)展示对象对所述第一内容数据的关注时长。
在一实施方式中,所述关注信息包括:用于指示展示对象是否对所述第一内容数据进行关注的指示信息;相应地,所述基于所述至少一个展示对象的地理位置信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息,包括:基于所述至少一个展示对象的地理位置信息,确定所述至少一个展示对象的位置是否落入第一区域范围,所述第一区域范围基于所述显示装置的位置确定(例如第一区域范围是以显示装置所在的位置为中心半径为预设长度的区域);对于位置落入所述第一区域范围的展示对象,所述展示对象对应的指示信息用于指示所述展示对象对所述第一内容数据进行关注;对于位置未落入所述第一区域范围的展示对象,所述展示对象对应的指示信息用于指示所述展示对象对所述第一内容数据未进行关注。
例如:获取到5个展示对象(展示对象1至展示对象5)的地理位置信息,分别为D1、D2、D3、D4、D5,应理解,地理位置信息基于不同的坐标系具有不同的表示形式。其中,D1、D3落入了第一区域范围,D2、D4、D5未落入第一内容数据所在的第一区域范围,则展示对象1和展示对象3对第一内容数据进行了关注,展示对象2、展示对象4以及展示对象5未对第一内容数据进行关注。
在一实施方式中,所述关注信息还包括:展示对象对所述第一内容数据的关注时长;所述基于所述至少一个展示对象的地理位置信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息,还包括:对于位置落入所述第一区域范围的展示对象,统计所述展示对象的位置落入所述第一区域范围的时长,基于所统计的时长确定所述展示对象对所述第一内容数据的关注时长。
例如:获取到5个展示对象(展示对象1至展示对象5)的地理位置信息,分别为D1、D2、D3、D4、D5,其中,D1、D3落入了第一区域范围,则展示对象1和展示对象3对第一内容数据进行了关注,对于展示对象1而言,其关注第一内容数据的时长为D1落入所述第一区域范围的时长T1,同理,对于展示对象3而言,其关注第一内容数据的时长为D3落入所述第一区域范围的时长T3。
本申请实施例中,展示对象与第一内容数据之间的关注信息可以包括上述其中一种或任意两种以上信息。
步骤403:获取至少一个展示对象的地理位置信息,基于所述至少一个展示对象的地理位置信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息。
承接步骤402,不同的关注信息可以作为不同的维度来对后续进行信息的推荐提供重要的参考。因此需要基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据的如下关注信息的至少之一进行统计:关注所述第一内容数据的人数、不同关注时长对应的人数。
在一个例子中,在统计周期(如3个小时)内,对信息1进行关注信息的统计,得到如下至少一种信息:关注信息1的人数为20个;关注信息1且关注时长位于第一时长范围内的人数为2个,关注信息1且关注时长位于第二时长范围内的人数为5个,关注信息1且关注时长位于第三时长范围内的人数为13个。
上述统计出的不同信息在不同的维度均可以衡量展示对象对第一内容数据的关注情况,可以将上述信息的一种或多种作为参考,来衡量第一内容数据的有效曝光程度(也即有效被观看的程度),从而可以为后续进行信息的精准推荐提供重要的参考。
本申请实施例中,展示对象的地理位置信息可以通过摄像头、或导航定位系统来获取得到,因而实现起来极为方便快捷,成本较低,通过地理位置信息所确定的关注信息作为后续推荐信息的参考,可以实现符合大部分展示对象的推荐需求,使得推荐信息的 曝光效果大大提高。
图5为本申请实施例的关注信息的处理方法的流程示意图四,如图5所示,所述关注信息的处理方法包括以下步骤:
步骤501:展示第一内容数据。
本申请实施例中,第一内容数据可以是任意一种推荐信息,推荐信息可以但不局限于是静态图像、动态图像、短视频、长视频、互动游戏等等。在一个例子中,第一内容数据可以是广告。
本申请实施例中,显示装置可以是普通的显示屏、一体机、投影仪、VR设备、AR设备等等。
步骤502:获取至少一个展示对象与所述第一内容数据之间的交互信息,基于所述至少一个展示对象与所述第一内容数据之间的交互信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息。
展示对象对第一内容数据的交互(如浏览操作、下载操作、点赞操作、关注操作、点击操作等等)能代表该展示对象对第一内容数据是否进行了关注,如果该展示对象对第一内容数据进行了关注,进一步还可以确定出该展示对象对第一内容数据的交互频次(单位时间内触发的交互操作的次数)。
在一实施方式中,所述关注信息包括:展示对象与所述第一内容数据之间的交互信息。
例如:5个展示对象(展示对象1至展示对象5)对第一内容数据进行了交互操作,其中在统计周期内,展示对象1对第一内容数据进行操作的次数为N1,展示对象2对第一内容数据进行操作的次数为N2,展示对象3对第一内容数据进行操作的次数为N3,展示对象4对第一内容数据进行操作的次数为N4,展示对象5对第一内容数据进行操作的次数为N5,那么N1至N5可以代表5个展示对象与第一内容数据之间的交互信息。不局限于此,还可以根据各个展示对象对第一内容数据进行操作的时长来衡量交互信息。
步骤503:基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据进行关注信息的统计。
承接步骤502,不同的关注信息可以作为不同的维度来对后续进行信息的推荐提供重要的参考。因此需要基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据的如下关注信息的至少之一进行统计:不同交互频次对应的人数。
在一个例子中,在统计周期(如3个小时)内,对信息1进行关注信息的统计,得到如下信息:与信息1进行交互的频次位于第一频次范围内的人数为6个,与信息1进行交互的频次位于第二频次范围内的人数为25个。
本申请实施例中,展示对象的交互信息可以直接通过显示装置或远程遥控装置获取得到,无需额外的设备来辅助,因而实现起来极为方便快捷,成本较低,通过交互信息所确定的关注信息能够准确地表明关注信息,基于这种关注信息作为后续推荐信息的参考,能够实现更加精准的信息推荐,更加符合展示对象的需求,使得推荐信息的曝光效果大大提高。
图6为本申请实施例的关注信息的处理装置的结构组成示意图一,如图6所示,所述关注信息的处理装置包括:
显示单元601,配置为展示第一内容数据;
获取单元602,配置为获取至少一个展示对象的特征信息;
确定单元603,配置为基于所述至少一个展示对象的特征信息,确定所述至少一个 展示对象与所述第一内容数据之间的关注信息;
统计单元604,配置为基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据进行关注信息的统计。
本领域技术人员应当理解,图6所示的关注信息的处理装置中的各单元的实现功能可参照前述关注信息的处理方法的相关描述而理解。图6所示的关注信息的处理装置中的各单元的功能可通过运行于处理器上的程序而实现,也可通过具体的逻辑电路而实现。
图7为本申请实施例的关注信息的处理装置的结构组成示意图二,如图7所示,所述关注信息的处理装置包括:
显示单元601,配置为展示第一内容数据;
获取单元602,配置为获取至少一个展示对象的特征信息;
确定单元603,配置为基于所述至少一个展示对象的特征信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息;
统计单元604,配置为基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据进行关注信息的统计。
在一实施方式中,所述装置还包括:
推荐单元605,配置为基于所统计出的关注信息,推荐待展示的第二内容数据;
所述展示单元,还配置为在所述显示装置上展示所述第二内容数据。
在一实施方式中,所述获取单元602,配置为获取至少一个展示对象的视线方向信息;
所述确定单元603,配置为基于所述至少一个展示对象的视线方向信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息。
在一实施方式中,所述关注信息包括:用于指示展示对象是否对所述第一内容数据进行关注的指示信息;所述确定单元603包括:
第一确定子单元6031,配置为基于所述至少一个展示对象的视线方向信息,确定所述至少一个展示对象的视线是否落入第一显示区域,所述第一显示区域为所述第一内容数据在所述显示装置上的显示区域;对于视线落入所述第一显示区域的展示对象,所述展示对象对应的指示信息用于指示所述展示对象对所述第一内容数据进行关注;对于视线未落入所述第一显示区域的展示对象,所述展示对象对应的指示信息用于指示所述展示对象对所述第一内容数据未进行关注。
在一实施方式中,所述关注信息还包括:展示对象对所述第一内容数据的关注程度;所述确定单元603还包括:
第二确定子单元6032,配置为对于视线落入所述第一显示区域的展示对象,基于所述展示对象的视线方向信息,确定所述展示对象的视线投射到所述第一显示区域的目标位置,并基于所述目标位置相对于所述第一显示区域的位置关系,确定所述展示对象对所述第一内容数据的关注程度。
在一实施方式中,所述关注信息还包括:展示对象对所述第一内容数据的关注时长;所述确定单元603还包括:
第三确定子单元6033,配置为对于视线落入所述第一显示区域的展示对象,统计所述展示对象的视线落入所述第一显示区域的时长,基于所统计的时长确定所述展示对象对所述第一内容数据的关注时长。
在一实施方式中,所述获取单元602包括:
获取子单元6021,配置为获取至少一个展示对象的眼珠转角信息和头部姿态信息;
计算子单元6022,配置为基于所述至少一个展示对象的眼珠转角信息和头部姿态信 息,计算所述至少一个展示对象的视线方向信息。
在一实施方式中,所述获取子单元6021,配置为:
获取所述至少一个展示对象的图像;
利用第一神经网络对所述至少一个展示对象的图像进行处理,得到所述至少一个展示对象的眼珠转角信息;
利用第二神经网络对所述至少一个展示对象的图像进行处理,得到所述至少一个展示对象的头部姿态信息。
在一实施方式中,所述统计单元604,配置为基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据的如下关注信息的至少之一进行统计:关注所述第一内容数据的人数、不同关注程度对应的人数、不同关注时长对应的人数。
在一实施方式中,所述获取单元602,配置为获取至少一个展示对象的地理位置信息;
所述确定单元603,配置为基于所述至少一个展示对象的地理位置信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息。
在一实施方式中,所述关注信息包括:用于指示展示对象是否对所述第一内容数据进行关注的指示信息;所述确定单元603包括:
第四确定子单元6034,配置为基于所述至少一个展示对象的地理位置信息,确定所述至少一个展示对象的位置是否落入第一区域范围,所述第一区域范围基于所述显示装置的位置确定;对于位置落入所述第一区域范围的展示对象,所述展示对象对应的指示信息用于指示所述展示对象对所述第一内容数据进行关注;对于位置未落入所述第一区域范围的展示对象,所述展示对象对应的指示信息用于指示所述展示对象对所述第一内容数据未进行关注。
在一实施方式中,所述关注信息还包括:展示对象对所述第一内容数据的关注时长;所述确定单元603包括:
第五确定子单元6035,配置为对于位置落入所述第一区域范围的展示对象,统计所述展示对象的位置落入所述第一区域范围的时长,基于所统计的时长确定所述展示对象对所述第一内容数据的关注时长。
在一实施方式中,所述统计单元604,配置为基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据的如下关注信息的至少之一进行统计:关注所述第一内容数据的人数、不同关注时长对应的人数。
在一实施方式中,所述获取单元602,配置为获取至少一个展示对象与所述第一内容数据之间的交互信息;
所述确定单元603,配置为基于所述至少一个展示对象与所述第一内容数据之间的交互信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息。
在一实施方式中,所述统计单元604,配置为基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据的如下关注信息进行统计:不同交互频次对应的人数。
本领域技术人员应当理解,图7所示的关注信息的处理装置中的各单元的实现功能可参照前述关注信息的处理方法的相关描述而理解。图7所示的关注信息的处理装置中的各单元的功能可通过运行于处理器上的程序而实现,也可通过具体的逻辑电路而实现。
本申请实施例还提供了一种电子设备,例如可以是移动终端、个人计算机(PC)、平板电脑、服务器等。图8为本申请实施例中电子设备一个应用实施例的结构示意图。 下面参考图8,其示出了适于用来实现本申请实施例的显示装置或服务器的电子设备1500的结构示意图:如图8所示,电子设备1500包括一个或多个处理器、通信部等,所述一个或多个处理器例如:一个或多个中央处理单元(CPU)1501,和/或一个或多个图像处理器(GPU)1513等,处理器可以根据存储在只读存储器(ROM)1502中的可执行指令或者从存储部分1508加载到随机访问存储器(RAM)1503中的可执行指令而执行各种适当的动作和处理。通信部1512可包括但不限于网卡,所述网卡可包括但不限于IB(Infiniband)网卡,处理器可与只读存储器1502和/或随机访问存储器1503中通信以执行可执行指令,通过总线1504与通信部1512相连、并经通信部1512与其他目标设备通信,从而完成本申请实施例提供的任一方法对应的操作。
此外,在RAM 1503中,还可存储有装置操作所需的各种程序和数据。CPU1501、ROM1502以及RAM1503通过总线1504彼此相连。在有RAM1503的情况下,ROM1502为可选模块。RAM1503存储可执行指令,或在运行时向ROM1502中写入可执行指令,可执行指令使处理器1501执行上述通信方法对应的操作。输入/输出(I/O)接口1505也连接至总线1504。通信部1512可以集成设置,也可以设置为具有多个子模块(例如多个IB网卡),并在总线链接上。
以下部件连接至I/O接口1505:包括键盘、鼠标等的输入部分1506;包括诸如阴极射线管(CRT)、液晶显示器(LCD)等以及扬声器等的输出部分1507;包括硬盘等的存储部分1508;以及包括诸如LAN卡、调制解调器等的网络接口卡的通信部分1509。通信部分1509经由诸如因特网的网络执行通信处理。驱动器1510也根据需要连接至I/O接口1505。可拆卸介质1511,诸如磁盘、光盘、磁光盘、半导体存储器等等,根据需要安装在驱动器1510上,以便于从其上读出的计算机程序根据需要被安装入存储部分1508。
需要说明的,如图8所示的架构仅为一种可选实现方式,在具体实践过程中,可根据实际需要对上述图8的部件数量和类型进行选择、删减、增加或替换;在不同功能部件设置上,也可采用分离设置或集成设置等实现方式,例如GPU和CPU可分离设置或者可将GPU集成在CPU上,通信部可分离设置,也可集成设置在CPU或GPU上,等等。这些可替换的实施方式均落入本申请公开的保护范围。
特别地,根据本公开的实施例,上文参考流程图描述的过程可以被实现为计算机软件程序。例如,本公开的实施例包括一种计算机程序产品,其包括有形地包含在机器可读介质上的计算机程序,计算机程序包含用于执行流程图所示的方法的程序代码,程序代码可包括对应执行本申请实施例提供的方法步骤对应的指令。在这样的实施例中,该计算机程序可以通过通信部分1509从网络上被下载和安装,和/或从可拆卸介质1511被安装。在该计算机程序被中央处理单元(CPU)1501执行时,执行本申请的方法中限定的上述功能。
本申请实施例的视线追踪技术方案可以应用于司机监控、广告分析、人机交互、安防监控、医疗诊断、心理学研究等各个方面。例如,应用于司机监控时,可以通过本申请实施例的视线追踪方法或装置判断司机视线方向,判断其关注点是否合理,与驾驶行为是否吻合,可以在司机走神时做出提醒,辅助其安全行驶。又如,应用于人机交互时,可以通过本申请实施例的视线追踪方法或装置获得实现方向,由视线方向和人眼位置估计得出展示对象的视线落点,进行人机交互,例如视线打字,视线操作等。再如,应用于安防监控时,可以通过本申请实施例的视线追踪方法或装置获得实现方向,根据人的视线方向判断其注意力方向,预测其后续行为。
本说明书中各个实施例均采用递进的方式描述,每个实施例重点说明的都是与其它实施例的不同之处,各个实施例之间相同或相似的部分相互参见即可。对于装置、系统 实施例而言,由于其与方法实施例基本对应,所以描述的比较简单,相关之处参见方法实施例的部分说明即可。
可能以许多方式来实现本申请的方法、装置和系统。例如,可通过软件、硬件、固件或者软件、硬件、固件的任何组合来实现本申请的方法、装置和系统。用于所述方法的步骤的上述顺序仅是为了进行说明,本申请的方法的步骤不限于以上具体描述的顺序,除非以其它方式特别说明。此外,在一些实施例中,还可将本申请实施为记录在记录介质中的程序,这些程序包括用于实现根据本申请的方法的机器可读指令。因而,本申请还覆盖存储用于执行根据本申请的方法的程序的记录介质。
本申请的描述是为了示例和描述起见而给出的,而并不是无遗漏的或者将本申请限于所公开的形式。很多修改和变化对于本领域的普通技术人员而言是显然的。选择和描述实施例是为了更好说明本申请的原理和实际应用,并且使本领域的普通技术人员能够理解本申请从而设计适于特定用途的带有各种修改的各种实施例。

Claims (36)

  1. 一种关注信息的处理方法,所述方法包括:
    展示第一内容数据;
    获取至少一个展示对象的特征信息,基于所述至少一个展示对象的特征信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息;
    基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据进行关注信息的统计。
  2. 根据权利要求1所述的方法,其中,所述方法还包括:
    基于所统计出的关注信息,推荐待展示的第二内容数据;
    展示所述第二内容数据。
  3. 根据权利要求1所述的方法,其中,所述获取至少一个展示对象的特征信息,基于所述至少一个展示对象的特征信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息,包括:
    获取至少一个展示对象的视线方向信息,基于所述至少一个展示对象的视线方向信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息。
  4. 根据权利要求3所述的方法,其中,所述关注信息包括:用于指示展示对象是否对所述第一内容数据进行关注的指示信息;
    所述基于所述至少一个展示对象的视线方向信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息,包括:
    基于所述至少一个展示对象的视线方向信息,确定所述至少一个展示对象的视线是否落入第一显示区域,所述第一显示区域为所述第一内容数据在所述显示装置上的显示区域。
  5. 根据权利要求4所述的方法,其中,
    对于视线落入所述第一显示区域的展示对象,所述展示对象对应的指示信息用于指示所述展示对象对所述第一内容数据进行关注;
    对于视线未落入所述第一显示区域的展示对象,所述展示对象对应的指示信息用于指示所述展示对象对所述第一内容数据未进行关注。
  6. 根据权利要求4或5所述的方法,其中,所述关注信息还包括:展示对象对所述第一内容数据的关注程度;
    所述基于所述至少一个展示对象的视线方向信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息,还包括:
    对于视线落入所述第一显示区域的展示对象,基于所述展示对象的视线方向信息,确定所述展示对象的视线投射到所述第一显示区域的目标位置,并基于所述目标位置相对于所述第一显示区域的位置关系,确定所述展示对象对所述第一内容数据的关注程度。
  7. 根据权利要求4或5所述的方法,其中,所述关注信息还包括:展示对象对所述第一内容数据的关注时长;
    所述基于所述至少一个展示对象的视线方向信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息,还包括:
    对于视线落入所述第一显示区域的展示对象,统计所述展示对象的视线落入所述第一显示区域的时长,基于所统计的时长确定所述展示对象对所述第一内容数据的关注时长。
  8. 根据权利要求3至7中任一项所述的方法,其中,所述获取至少一个展示对象的视线方向信息,包括:
    获取至少一个展示对象的眼珠转角信息和头部姿态信息;
    基于所述至少一个展示对象的眼珠转角信息和头部姿态信息,计算所述至少一个展示对象的视线方向信息。
  9. 根据权利要求8所述的方法,其中,所述获取至少一个展示对象的眼珠转角信息和头部姿态信息,包括:
    获取所述至少一个展示对象的图像;
    利用第一神经网络对所述至少一个展示对象的图像进行处理,得到所述至少一个展示对象的眼珠转角信息;
    利用第二神经网络对所述至少一个展示对象的图像进行处理,得到所述至少一个展示对象的头部姿态信息。
  10. 根据权利要求3至9任一项所述的方法,其中,所述基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据进行关注信息的统计,包括:
    基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据的如下关注信息的至少之一进行统计:关注所述第一内容数据的人数、不同关注程度对应的人数、不同关注时长对应的人数。
  11. 根据权利要求1所述的方法,其中,所述获取至少一个展示对象的特征信息,基于所述至少一个展示对象的特征信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息,包括:
    获取至少一个展示对象的地理位置信息,基于所述至少一个展示对象的地理位置信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息。
  12. 根据权利要求11所述的方法,其中,所述关注信息包括:用于指示展示对象是否对所述第一内容数据进行关注的指示信息;
    所述基于所述至少一个展示对象的地理位置信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息,包括:
    基于所述至少一个展示对象的地理位置信息,确定所述至少一个展示对象的位置是否落入第一区域范围,所述第一区域范围基于所述显示装置的位置确定。
  13. 根据权利要求12所述的方法,其中,
    对于位置落入所述第一区域范围的展示对象,所述展示对象对应的指示信息用于指示所述展示对象对所述第一内容数据进行关注;
    对于位置未落入所述第一区域范围的展示对象,所述展示对象对应的指示信息用于指示所述展示对象对所述第一内容数据未进行关注。
  14. 根据权利要求12或13所述的方法,其中,所述关注信息还包括:展示对象对所述第一内容数据的关注时长;
    所述基于所述至少一个展示对象的地理位置信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息,还包括:
    对于位置落入所述第一区域范围的展示对象,统计所述展示对象的位置落入所述第一区域范围的时长,基于所统计的时长确定所述展示对象对所述第一内容数据的关注时长。
  15. 根据权利要求11至14任一项所述的方法,其中,所述基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据进行关注信息的统计,包括:
    基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据的如下关注信息的至少之一进行统计:关注所述第一内容数据的人数、不同关注时长对应的人数。
  16. 根据权利要求1所述的方法,其中,所述获取至少一个展示对象的特征信息,基于所述至少一个展示对象的特征信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息,包括:
    获取至少一个展示对象与所述第一内容数据之间的交互信息,基于所述至少一个展示对象与所述第一内容数据之间的交互信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息。
  17. 根据权利要求16所述的方法,其中,所述基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据进行关注信息的统计,包括:
    基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据的如下关注信息进行统计:不同交互频次对应的人数。
  18. 一种关注信息的处理装置,所述装置包括:
    显示单元,配置为展示第一内容数据;
    获取单元,配置为获取至少一个展示对象的特征信息;
    确定单元,配置为基于所述至少一个展示对象的特征信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息;
    统计单元,配置为基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据进行关注信息的统计。
  19. 根据权利要求18所述的装置,其中,所述装置还包括:
    推荐单元,配置为基于所统计出的关注信息,推荐待展示的第二内容数据;
    所述展示单元,还配置为展示所述第二内容数据。
  20. 根据权利要求18所述的装置,其中,
    所述获取单元,配置为获取至少一个展示对象的视线方向信息;
    所述确定单元,配置为基于所述至少一个展示对象的视线方向信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息。
  21. 根据权利要求20所述的装置,其中,所述关注信息包括:用于指示展示对象是否对所述第一内容数据进行关注的指示信息;所述确定单元包括:
    第一确定子单元,配置为基于所述至少一个展示对象的视线方向信息,确定所述至少一个展示对象的视线是否落入第一显示区域,所述第一显示区域为所述第一内容数据在所述显示装置上的显示区域。
  22. 根据权利要求21所述的装置,其中,
    对于视线落入所述第一显示区域的展示对象,所述展示对象对应的指示信息用于指示所述展示对象对所述第一内容数据进行关注;对于视线未落入所述第一显示区域的展示对象,所述展示对象对应的指示信息用于指示所述展示对象对所述第一内容数据未进行关注。
  23. 根据权利要求21或22所述的装置,其中,所述关注信息还包括:展示对象对所述第一内容数据的关注程度;所述确定单元还包括:
    第二确定子单元,配置为对于视线落入所述第一显示区域的展示对象,基于所述展示对象的视线方向信息,确定所述展示对象的视线投射到所述第一显示区域的目标位置,并基于所述目标位置相对于所述第一显示区域的位置关系,确定所述展示对象对所述第一内容数据的关注程度。
  24. 根据权利要求21或22所述的装置,其中,所述关注信息还包括:展示对象对 所述第一内容数据的关注时长;所述确定单元还包括:
    第三确定子单元,配置为对于视线落入所述第一显示区域的展示对象,统计所述展示对象的视线落入所述第一显示区域的时长,基于所统计的时长确定所述展示对象对所述第一内容数据的关注时长。
  25. 根据权利要求20至24中任一项所述的装置,其中,所述获取单元包括:
    获取子单元,配置为获取至少一个展示对象的眼珠转角信息和头部姿态信息;
    计算子单元,配置为基于所述至少一个展示对象的眼珠转角信息和头部姿态信息,计算所述至少一个展示对象的视线方向信息。
  26. 根据权利要求25所述的装置,其中,所述获取子单元,配置为:
    获取所述至少一个展示对象的图像;
    利用第一神经网络对所述至少一个展示对象的图像进行处理,得到所述至少一个展示对象的眼珠转角信息;
    利用第二神经网络对所述至少一个展示对象的图像进行处理,得到所述至少一个展示对象的头部姿态信息。
  27. 根据权利要求20至26任一项所述的装置,其中,所述统计单元,配置为基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据的如下关注信息的至少之一进行统计:关注所述第一内容数据的人数、不同关注程度对应的人数、不同关注时长对应的人数。
  28. 根据权利要求18所述的装置,其中,
    所述获取单元,配置为获取至少一个展示对象的地理位置信息;
    所述确定单元,配置为基于所述至少一个展示对象的地理位置信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息。
  29. 根据权利要求28所述的装置,其中,所述关注信息包括:用于指示展示对象是否对所述第一内容数据进行关注的指示信息;所述确定单元包括:
    第四确定子单元,配置为基于所述至少一个展示对象的地理位置信息,确定所述至少一个展示对象的位置是否落入第一区域范围,所述第一区域范围基于所述显示装置的位置确定。
  30. 根据权利要求29所述的装置,其中,
    对于位置落入所述第一区域范围的展示对象,所述展示对象对应的指示信息用于指示所述展示对象对所述第一内容数据进行关注;对于位置未落入所述第一区域范围的展示对象,所述展示对象对应的指示信息用于指示所述展示对象对所述第一内容数据未进行关注。
  31. 根据权利要求29或30所述的装置,其中,所述关注信息还包括:展示对象对所述第一内容数据的关注时长;所述确定单元包括:
    第五确定子单元,配置为对于位置落入所述第一区域范围的展示对象,统计所述展示对象的位置落入所述第一区域范围的时长,基于所统计的时长确定所述展示对象对所述第一内容数据的关注时长。
  32. 根据权利要求28至31任一项所述的装置,其中,所述统计单元,配置为基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据的如下关注信息的至少之一进行统计:关注所述第一内容数据的人数、不同关注时长对应的人数。
  33. 根据权利要求18所述的装置,其中,
    所述获取单元,配置为获取至少一个展示对象与所述第一内容数据之间的交互信息;
    所述确定单元,配置为基于所述至少一个展示对象与所述第一内容数据之间的交互信息,确定所述至少一个展示对象与所述第一内容数据之间的关注信息。
  34. 根据权利要求33所述的装置,其中,所述统计单元,配置为基于所述至少一个展示对象与所述第一内容数据之间的关注信息,对所述第一内容数据的如下关注信息进行统计:不同交互频次对应的人数。
  35. 一种存储介质,所述存储介质上存储有可执行指令,该可执行指令被处理器执行时实现权利要求1至17任一项所述的方法步骤。
  36. 一种电子设备,所述电子设备包括:
    存储器,配置为存储可执行指令;
    处理器,配置为与所述存储器通信以执行所述可执行指令从而实现权利要求1至17任一所述的方法步骤。
PCT/CN2019/083442 2018-04-24 2019-04-19 一种关注信息的处理方法及装置、存储介质、电子设备 WO2019206038A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
SG11202010556WA SG11202010556WA (en) 2018-04-24 2019-04-19 Methods and apparatuses for processing attention information, storage media and electronic devices
JP2020558903A JP7130771B2 (ja) 2018-04-24 2019-04-19 注目情報の処理方法および装置、記憶媒体ならびに電子機器

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201810374723.6 2018-04-24
CN201810374723.6A CN108563778B (zh) 2018-04-24 2018-04-24 一种关注信息的处理方法及装置、存储介质、电子设备

Publications (1)

Publication Number Publication Date
WO2019206038A1 true WO2019206038A1 (zh) 2019-10-31

Family

ID=63536709

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/083442 WO2019206038A1 (zh) 2018-04-24 2019-04-19 一种关注信息的处理方法及装置、存储介质、电子设备

Country Status (4)

Country Link
JP (1) JP7130771B2 (zh)
CN (1) CN108563778B (zh)
SG (1) SG11202010556WA (zh)
WO (1) WO2019206038A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112597653A (zh) * 2020-12-24 2021-04-02 南京城建隧桥经营管理有限责任公司 一种户外多媒体平台信息显示时长确定方法
JP2022161690A (ja) * 2021-04-09 2022-10-21 本田技研工業株式会社 情報処理装置、情報処理方法、学習方法、およびプログラム

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108563778B (zh) * 2018-04-24 2022-11-04 北京市商汤科技开发有限公司 一种关注信息的处理方法及装置、存储介质、电子设备

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102934458A (zh) * 2011-02-04 2013-02-13 松下电器产业株式会社 兴趣度估计装置以及兴趣度估计方法
CN103760968A (zh) * 2013-11-29 2014-04-30 理光软件研究所(北京)有限公司 数字标牌显示内容选择方法和装置
CN104462468A (zh) * 2014-12-17 2015-03-25 百度在线网络技术(北京)有限公司 信息提供方法及装置
CN104823152A (zh) * 2012-12-19 2015-08-05 高通股份有限公司 使用视线追踪实现扩增实境
CN105989045A (zh) * 2015-02-04 2016-10-05 华为技术有限公司 一种劝导内容推荐的方法、装置及系统
CN106557937A (zh) * 2015-09-24 2017-04-05 杭州海康威视数字技术股份有限公司 广告推送方法和装置
CN108563778A (zh) * 2018-04-24 2018-09-21 北京市商汤科技开发有限公司 一种关注信息的处理方法及装置、存储介质、电子设备

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
GR1001389B (el) * 1991-08-28 1993-10-29 Panagiotis Anagnostopoulos Μέ?οδος αυτομάτου δρομολογήσεως πλοηγήσεως, προστασίας και πληροφορήσεως οδηγών οχημάτων.
JP4061379B2 (ja) 2004-11-29 2008-03-19 国立大学法人広島大学 情報処理装置、携帯端末、情報処理方法、情報処理プログラム、およびコンピュータ読取可能な記録媒体
CN1293446C (zh) * 2005-06-02 2007-01-03 北京中星微电子有限公司 一种非接触式目控操作系统和方法
JP5272213B2 (ja) 2010-04-30 2013-08-28 日本電信電話株式会社 広告効果測定装置、広告効果測定方法およびプログラム
CN103300815B (zh) * 2012-03-15 2015-05-13 凹凸电子(武汉)有限公司 眼球关注点确定方法、装置和系统
CN103335644B (zh) * 2013-05-31 2016-03-16 王玉娇 街景地图的声音播放方法及相关设备
JP6237504B2 (ja) 2014-07-08 2017-11-29 株式会社デンソー 視線入力装置
US20170060864A1 (en) * 2015-08-26 2017-03-02 Quixey, Inc. Action Recommendation System for Focused Objects
US10303341B2 (en) 2016-05-25 2019-05-28 International Business Machines Corporation Modifying screen content based on gaze tracking and user distance from the screen
CN106339489A (zh) * 2016-08-31 2017-01-18 南京炫佳网络科技有限公司 动漫ip用户喜好度评估算法
CN107358459A (zh) * 2017-06-15 2017-11-17 浙江启冠网络股份有限公司 基于定向房产兴趣人群的广告投放方法与系统
CN107798102A (zh) * 2017-10-30 2018-03-13 北京金堤科技有限公司 一种页面展示方法及装置

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102934458A (zh) * 2011-02-04 2013-02-13 松下电器产业株式会社 兴趣度估计装置以及兴趣度估计方法
CN104823152A (zh) * 2012-12-19 2015-08-05 高通股份有限公司 使用视线追踪实现扩增实境
CN103760968A (zh) * 2013-11-29 2014-04-30 理光软件研究所(北京)有限公司 数字标牌显示内容选择方法和装置
CN104462468A (zh) * 2014-12-17 2015-03-25 百度在线网络技术(北京)有限公司 信息提供方法及装置
CN105989045A (zh) * 2015-02-04 2016-10-05 华为技术有限公司 一种劝导内容推荐的方法、装置及系统
CN106557937A (zh) * 2015-09-24 2017-04-05 杭州海康威视数字技术股份有限公司 广告推送方法和装置
CN108563778A (zh) * 2018-04-24 2018-09-21 北京市商汤科技开发有限公司 一种关注信息的处理方法及装置、存储介质、电子设备

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112597653A (zh) * 2020-12-24 2021-04-02 南京城建隧桥经营管理有限责任公司 一种户外多媒体平台信息显示时长确定方法
CN112597653B (zh) * 2020-12-24 2024-04-19 南京城建隧桥智慧管理有限公司 一种户外多媒体平台信息显示时长确定方法
JP2022161690A (ja) * 2021-04-09 2022-10-21 本田技研工業株式会社 情報処理装置、情報処理方法、学習方法、およびプログラム
JP7219788B2 (ja) 2021-04-09 2023-02-08 本田技研工業株式会社 情報処理装置、情報処理方法、学習方法、およびプログラム

Also Published As

Publication number Publication date
JP7130771B2 (ja) 2022-09-05
SG11202010556WA (en) 2020-11-27
CN108563778B (zh) 2022-11-04
JP2021518959A (ja) 2021-08-05
CN108563778A (zh) 2018-09-21

Similar Documents

Publication Publication Date Title
US20240298152A1 (en) Augmented reality identification of subscribers
AU2022218469B2 (en) Methods and systems for displaying information associated with a smart object
WO2019206038A1 (zh) 一种关注信息的处理方法及装置、存储介质、电子设备
US20240144628A1 (en) Methods and systems for generating digital objects for collecting data in a three-dimensional environment
US20190333099A1 (en) Method and system for ip address traffic based detection of fraud
US20180268439A1 (en) Dynamically generating and delivering sequences of personalized multimedia content
AU2017334312B2 (en) Objective based advertisement placement platform
US8799098B2 (en) Customized marketing
US20220027931A1 (en) System to calculate engagement score of location based media content
US20160232562A1 (en) System and method for direct response advertising
CN112232854A (zh) 业务处理方法、装置、设备及存储介质
US20130138498A1 (en) Flash sale
US20140179354A1 (en) Determining contact opportunities
KR20150034925A (ko) 매장의 디스플레이 장치를 이용한 광고 방법 및 장치
US20240137615A1 (en) Methods and systems for counseling a user with respect to supervised content
CN113781084A (zh) 一种调查问卷展示方法和装置
US20170358004A1 (en) System, method, and recording medium for location-based advertisement
CN107786376B (zh) 内容推送方法、装置及计算机设备
US10650405B2 (en) Media content tracking
CN113419798B (zh) 内容的展示方法、装置、设备和存储介质
US10776860B2 (en) Retail website user interface, systems, and methods for displaying trending looks
US11233865B2 (en) Visitor engagement detection and control for online sessions with a listing platform
CN114066507A (zh) 推广信息的分析方法、装置、电子设备及存储介质
US20170358002A1 (en) System, method, and recording medium for advertisement remarketing
US20140358696A1 (en) Advertisement system using retailer inventory

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19792738

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2020558903

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19792738

Country of ref document: EP

Kind code of ref document: A1